Inference Engineer in San Francisco

About the Team OpenAI Consumer Devices is building the next generation of products that bring powerful AI into people’s everyday lives. Guided by OpenAI’s mission to ensure AGI benefits all of humanity, our team combines world-class researchers, engineers, designers, and operators who care deeply about creating useful, intuitive, and responsible technology. You’ll have the opportunity to work alongside exceptional people on ambitious, zero-to-one challenges at the intersection of hardware, software, and AI. This is a chance to help define an entirely new category of products—and shape how people experience AI in the future. Our team works across silicon, embedded systems, operating systems, and cloud services to build reliable consumer devices and the novel platforms required to support them. We partner closely with research to bring advanced AI capabilities into the physical world. About the Role As an Operating Systems Engineer focused on on-device inference, you will design, develop, and ship the OS stack that makes advanced AI capabilities reliable, responsive, and energy efficient on consumer devices. Your work will span OS services and frameworks, inference runtime integration, model fitting, scheduling, and performance and power management. You’ll partner with research to adapt models to device constraints, make design decisions across the stack, and carry solutions from early exploration through integration and production. In this role, you will: Build the inference platform: Design and implement maintainable OS services, frameworks, and clear interfaces for inference execution, model loading and lifecycle, and resource management. Fit models to device constraints: Partner with researchers on quantization, runtime integration, and memory optimization to meet memory, compute, and energy budgets while evaluating model quality and product behavior. Coordinate system resources: Develop scheduling and resource policies that balance inference with other device act

ABOUT BASETEN Baseten powers mission-critical inference for the world's most dynamic AI companies, like Cursor, Notion, OpenEvidence, Abridge, Clay, Gamma, and Writer. By uniting applied AI research, flexible infrastructure, and seamless developer tooling, we enable companies operating at the frontier of AI to bring cutting-edge models into production. We're growing quickly and recently raised our $1.5B Series F , led by Altimeter Capital, Conviction Partners, and Spark Capital. Join us and help build the platform engineers turn to ship AI products. THE ROLE Baseten's Compute org is in hyper growth. As it scales, the systems and workflows that keep supply and demand balanced across our GPU fleet need to get more sophisticated, and this role exists to make sure they do. Compute sits at the center of how Baseten allocates, forecasts, and manages the capacity that powers every customer inference request. The team that supports this work, C3, runs on a mix of internal tooling, manual processes, and systems that haven't fully kept pace with the scale of the problem. This role exists to close that gap. You'll design, build, and ship AI-powered workflows that give the Compute and C3 teams real leverage, automating the manual, repetitive, and error-prone parts of the capacity lifecycle so the team can focus on judgment calls that actually need a human. We want someone who can walk in, audit what exists today, identify what's missing or broken, and start shipping fast. You know when to reach for an existing internal tool and when to build something custom in Claude Code. You think two to three steps ahead about how the thing you build today fits into the broader capacity systems architecture tomorrow. And you bring a point of view on our stack, on what we should be building, and on where AI can do something existing tooling simply can't. RESPONSIBILITIES Ship AI-powered workflows for Compute and C3 : build the agents and automations that give capacity analysts, ops leads, an

ABOUT BASETEN Baseten powers mission-critical inference for the world's most dynamic AI companies, like Cursor, Notion, OpenEvidence, Abridge, Clay, Gamma, and Writer. By uniting applied AI research, flexible infrastructure, and seamless developer tooling, we enable companies operating at the frontier of AI to bring cutting-edge models into production. We're growing quickly and recently raised our $1.5B Series F , led by Altimeter Capital, Conviction Partners, and Spark Capital. Join us and help build the platform engineers turn to ship AI products. THE ROLE The largest, most demanding enterprises run on Baseten, and they bring exacting requirements for how people, services, and agents access the platform. This is the founding role for our identity and authorization team within enterprise engineering. You'll own the identity and access layer of the Baseten platform: the authorization model, credential systems, and admin experiences that enterprise IT teams use to govern access for organizations like Harvey, HubSpot, and Notion. You'll design and build Baseten's fine-grained authorization system from the ground up to support the workflows customers depend on today while giving them cleaner, more precise ways to manage access as the platform grows. Authorization at Baseten requires low-latency permission checks at high request volume, consistent contracts and behaviors across the product suite, and strong security guarantees for mission-critical, highly regulated workloads. EXAMPLE INITIATIVES Recent and upcoming work in this area: Fine-grained authorization for users, service accounts, and agentic workloads: per-resource permissions at the organization, team, and workload scope to support both common workflows and complex enterprise access policies Programmatic authentication allowing high-compliance customers to connect service principles securely via short-lived, workload-based credentials Agent credentials that grant an agent exactly the access it needs for the gi

ABOUT BASETEN Baseten powers mission-critical inference for the world's most dynamic AI companies, like Cursor, Notion, OpenEvidence, Abridge, Clay, Gamma and Writer. By uniting applied AI research, flexible infrastructure, and seamless developer tooling, we enable companies operating at the frontier of AI to bring cutting-edge models into production. We're growing quickly and recently raised our $1.5B Series F , led by Altimeter Capital, Conviction Partners, and Spark Capital. Join us and help build the platform engineers turn to to ship AI products. THE ROLE We're looking for a Web Designer / Design Engineer to own baseten.co day to day, from concept through production. You'll design and build landing pages, bring product launches to life, run experiments, improve conversion, and keep raising the quality bar on the site. This is a high-ownership role on the brand design team, sitting between brand design and frontend engineering. We want the website to be one of the best expressions of the Baseten brand and one of the best developer-focused sites on the internet, which means treating it as a product that's constantly evolving rather than something we redesign every few years. You'll have a lot of autonomy to ship, while partnering closely with brand, product marketing, engineering, and leadership on bigger launches. RESPONSIBILITIES Own the design and frontend implementation of the Baseten marketing site. Ship landing pages, product pages, launches, and campaigns from concept through production. Improve the site continuously, finding and acting on opportunities to make it better rather than waiting for a redesign cycle. Partner with growth and product marketing to test messaging, layouts, and conversion improvements without sacrificing craft. Build polished interactions, motion, and details that make the site feel distinctly Baseten. Build and evolve the components, patterns, and design systems that let the team move quickly without lowering the bar. Turn complex

ABOUT BASETEN Baseten powers mission-critical inference for the world's most dynamic AI companies, like Cursor, Notion, OpenEvidence, Abridge, Clay, Gamma and Writer. By uniting applied AI research, flexible infrastructure, and seamless developer tooling, we enable companies operating at the frontier of AI to bring cutting-edge models into production. We're growing quickly and recently raised our $1.5B Series F , led by Altimeter Capital, Conviction Partners, and Spark Capital. Join us and help build the platform engineers turn to to ship AI products. THE ROLE: Are you the person on your team who builds the agent everyone else ends up using? We're looking for an AI Engineer to join our Training Product team and do that at Baseten. You'll build AI-driven product features for the customers training and post-training frontier models on our platform, and you'll raise the ceiling on how Baseten itself uses AI internally, turning manual workflows into agentic ones that make every other team faster. You'll work directly with our research engineers to scope and build products, taking ideas from a research loop that already works internally to something customers can run themselves. This is a hands-on role with real autonomy. You'll pick the problems worth solving, build the harnesses, execution flows, and guardrails that make AI systems reliable, and own the results. If you've been shipping agents and want that to be the job, let's talk. EXAMPLE INITIATIVES: Take a look at these blog posts written by members of our team: Baseten Training: an autoresearch substrate Introducing Baseten Loops Harnesses are everything. Here's how to optimize yours. Building with NVIDIA Nemotron 3 Ultra and LangChain Deep Agents Code on Baseten RESPONSIBILITIES: Build and ship agentic product experiences, including chat-style and assistant-like interfaces, from prototype to GA. Design the harnesses, execution flows, and guardrails that make AI systems reliable in production. Build internal autom

ABOUT BASETEN Baseten powers mission-critical inference for the world's most dynamic AI companies, like Cursor, Notion, OpenEvidence, Abridge, Clay, Gamma and Writer. By uniting applied AI research, flexible infrastructure, and seamless developer tooling, we enable companies operating at the frontier of AI to bring cutting-edge models into production. We're growing quickly and recently raised our $1.5B Series F , led by Altimeter Capital, Conviction Partners, and Spark Capital. Join us and help build the platform engineers turn to to ship AI products. THE ROLE We are seeking an experienced and proactive Security Engineer to help us build, maintain, and continuously improve the security posture of our rapidly growing ML infrastructure platform. As one of the first dedicated security hires at Baseten, you will work cross-functionally with engineering and operations teams to ensure we’re meeting the highest standards of confidentiality, integrity, and availability. You’ll have an opportunity to shape our security strategy and best practices from the ground up, influencing the way our platform handles sensitive data for both internal and external stakeholders. RESPONSIBILITIES Security architecture and design: Collaborate with engineering teams to design and implement secure systems and infrastructure, including cloud (AWS/GCP) environments and container orchestration platforms. Vulnerability management: Lead proactive vulnerability assessments, pen tests, and remediation efforts to ensure our products and infrastructure remain secure. Incident response: Develop and maintain incident response processes, including detection, analysis, containment, eradication, and post-incident reviews. Identity and access management (IAM): Oversee IAM strategies and tools to ensure the right people have the right level of access to our systems and data. Security compliance and audits: Work closely with operations to ensure compliance with relevant standards (e.g., SOC 2, ISO 27001) and

ABOUT BASETEN Baseten powers mission-critical inference for the world's most dynamic AI companies, like Cursor, Notion, OpenEvidence, Abridge, Clay, Gamma and Writer. By uniting applied AI research, flexible infrastructure, and seamless developer tooling, we enable companies operating at the frontier of AI to bring cutting-edge models into production. We're growing quickly and recently raised our $1.5B Series F , led by Altimeter Capital, Conviction Partners, and Spark Capital. Join us and help build the platform engineers turn to to ship AI products. THE ROLE As an Infrastructure Software Engineer at Baseten, you'll build and maintain components of our ML inference platform that powers production AI applications. You'll contribute to the core infrastructure, enabling developers to deploy, scale, and monitor ML models with high performance. EXAMPLE INITIATIVES You'll get to work on these types of projects as part of our Infrastructure team: Multi-cloud capacity management Inference on B200 GPUs Multi-node inference Fractional H100 GPUs for efficient model serving RESPONSIBILITIES Develop infrastructure components for our ML inference platform using Python and Go Implement and maintain Kubernetes deployments for model serving Contribute to our inference orchestration layer for model deployments Build and enhance monitoring systems for model performance metrics Implement efficient resource management solutions for ML workloads Support infrastructure automation to improve ML deployment workflows Work closely with team members to implement technical solutions Help balance performance optimization with system reliability Participate in technical discussions around infrastructure improvements Learn and apply infrastructure best practices REQUIREMENTS Bachelor's degree or higher in Computer Science or related field Proficient coding abilities in one or more popular programming or scripting languages; Go proficiency is a plus Working knowledge of Kubernetes and containeriza

ABOUT BASETEN Baseten powers mission-critical inference for the world's most dynamic AI companies, like Cursor, Notion, OpenEvidence, Abridge, Clay, Gamma and Writer. By uniting applied AI research, flexible infrastructure, and seamless developer tooling, we enable companies operating at the frontier of AI to bring cutting-edge models into production. We're growing quickly and recently raised our $1.5B Series F , led by Altimeter Capital, Conviction Partners, and Spark Capital. Join us and help build the platform engineers turn to to ship AI products. THE ROLE Are you passionate about advancing the application of artificial intelligence? We are looking for a Software Engineer focused on ML performance to join our dynamic team. This role is ideal for someone who thrives in a fast-paced startup environment and is eager to make significant contributions to the exciting field of LLM Inference. If you are a backend engineer who thrives on making things faster and is excited about open-source ML models, we look forward to your application. EXAMPLE INITIATIVES You'll get to work on these types of projects as part of our Model Performance team: Baseten Embeddings Inference: The fastest embeddings solution available The Baseten Inference Stack Driving model performance optimization RESPONSIBILITIES Implement, refine, and productionize cutting-edge techniques (quantization, speculative decoding, kv cache reuse, chunked prefill and LoRA) for ML model inference and infrastructure. Deep dive into underlying codebases of TensorRT, PyTorch, TensorRT-LLM, vllm, sglang, CUDA, and other libraries to debug ML performance issues. Apply and scale optimization techniques across a wide range of ML models, particularly large language models. Collaborate with a diverse team to design and implement innovative solutions. Own projects from idea to production. REQUIREMENTS Bachelor's, Master's, or Ph.D. degree in Computer Science, Engineering, Mathematics, or related field. Experience with one

ABOUT BASETEN Baseten powers mission-critical inference for the world's most dynamic AI companies, like Cursor, Notion, OpenEvidence, Abridge, Clay, Gamma and Writer. By uniting applied AI research, flexible infrastructure, and seamless developer tooling, we enable companies operating at the frontier of AI to bring cutting-edge models into production. We're growing quickly and recently raised our $1.5B Series F , led by Altimeter Capital, Conviction Partners, and Spark Capital. Join us and help build the platform engineers turn to to ship AI products. THE ROLE As a Software Engineer on the Internal Tooling team, you will own the internal operating system that sits at the heart of how Baseten operates. Capacity helps unlock revenue by carefully balancing supply and demand. The operating system manages all aspects of the customer lifecycle: from onboarding to managing complex customer SLA requirements. This role is for engineers who want to own a product end to end, not just implement tickets. You will work directly with the Capacity, Sales, and Engineering teams to understand requirements, define solutions, and ship software that removes friction from some of the most high-stakes workflows in the company. If something is slow, manual, or error-prone in the capacity fulfillment lifecycle, you will be the one to fix it. You are a strong fit if you have strong product intuition, move fast without sacrificing quality, and take satisfaction in building tools that make the people around you measurably more effective. RESPONSIBILITIES Own the Capacity product end to end: scoping, design, implementation, and iteration based on feedback from internal stakeholders Translate complex operational requirements from Capacity, Sales, and SRE teams into clean, ergonomic product experiences Build and maintain full-stack features across the Capacity toolchain, including UI surfaces, APIs, and backend services Identify workflow bottlenecks and manual processes across the capacity lifecy

ABOUT BASETEN Baseten powers mission-critical inference for the world's most dynamic AI companies, like Cursor, Notion, OpenEvidence, Abridge, Clay, Gamma and Writer. By uniting applied AI research, flexible infrastructure, and seamless developer tooling, we enable companies operating at the frontier of AI to bring cutting-edge models into production. We're growing quickly and recently raised our $1.5B Series F , led by Altimeter Capital, Conviction Partners, and Spark Capital. Join us and help build the platform engineers turn to to ship AI products. THE ROLE Baseten's engineers want to work in an AI-first way. What's missing isn't enthusiasm — it's the platform underneath it. Today everyone assembles their own agent config, context files, and MCP servers, so the good patterns stay trapped in individual setups instead of becoming defaults everyone inherits. You'll build that platform: the agent configurations tuned to our monorepo, the context and tooling layer that makes agents competent in our codebase, the evals that tell us which approaches actually work, and the rollout mechanics that get a new engineer productive with agents in week one. You are not here to mandate how engineers use AI — you're here to make the good path the easy path. Success looks like teams adopting what you build because it beats what they'd cobble together themselves, not because a policy requires it. Platform engineer, not AI evangelist. Ship infrastructure, measure it, kill what doesn't work, let adoption be the referee. The playbook for AI-first SDLC doesn't exist at any company yet. You'll write ours. WHAT YOU'LL BUILD Agent substrate — Repo-level context infrastructure that makes agents competent in our codebase ( CLAUDE.md/AGENTS.md conventions, architecture and domain context, and the tooling to keep it accurate as code moves). Internal MCP servers giving agents scoped access to CI, observability, incident tooling, deployment state, and docs. Shared skills, subagents, and hooks th

ABOUT BASETEN Baseten powers mission-critical inference for the world's most dynamic AI companies, like Cursor, Notion, OpenEvidence, Abridge, Clay, Gamma and Writer. By uniting applied AI research, flexible infrastructure, and seamless developer tooling, we enable companies operating at the frontier of AI to bring cutting-edge models into production. We're growing quickly and recently raised our $1.5B Series F , led by Altimeter Capital, Conviction Partners, and Spark Capital. Join us and help build the platform engineers turn to to ship AI products. THE ROLE We’re seeking a GPU Kernel Engineer to join our team at the cutting edge of AI acceleration, where your code directly impacts the performance of state-of-the-art machine learning models. As a GPU Kernel Engineer, you'll craft the foundation that powers modern AI workloads, optimizing every microsecond of computation to enable breakthrough applications. You'll work in a fast-paced, intellectually stimulating environment where technical excellence is paramount and your contributions directly influence production systems serving millions of users across numerous products. This role offers exceptional growth potential for engineers passionate about low-level optimization and high-impact systems work. EXAMPLE INITIATIVES You'll get to work on these types of projects as part of our Model Performance team: Baseten Embeddings Inference: The fastest embeddings solution available The Baseten Inference Stack Driving model performance optimization RESPONSIBILITIES Core Engineering Responsibilities Design and implement high-performance GPU kernels for key ML operations, including matrix multiplications, attention mechanisms, and mixture-of-experts routing Write and optimize code using CUDA, PTX assembly, and architecture-specific techniques Apply advanced performance optimization methods such as memory coalescing, warp-level programming, tensor core acceleration, and compute/memory overlap Performance & Innovation Impl

ABOUT BASETEN Baseten powers mission-critical inference for the world's most dynamic AI companies, like Cursor, Notion, OpenEvidence, Abridge, Clay, Gamma and Writer. By uniting applied AI research, flexible infrastructure, and seamless developer tooling, we enable companies operating at the frontier of AI to bring cutting-edge models into production. We're growing quickly and recently raised our $1.5B Series F , led by Altimeter Capital, Conviction Partners, and Spark Capital. Join us and help build the platform engineers turn to to ship AI products. THE ROLE Baseten is seeking talented and experienced Software Engineers to join our Platform team within the Infrastructure organization. As a senior member of Baseten's Platform Team, you will own the systems that let every engineer at Baseten prove their code works before it reaches production. Our product runs mission-critical AI inference for customers who measure downtime in dollars per second, which means our internal bar for correctness, performance, and failure tolerance has to be exceptional. Your focus is the full testing stack: fast and reliable unit test tooling, integration harnesses that spin up realistic environments on demand, load and performance testing for GPU-backed inference workloads, and resilience testing that deliberately breaks things so our customers never have to find out what happens when a node dies mid-request. This is a builder role with org-wide leverage. You won't be writing tests for other teams — you'll be building the frameworks, harnesses, and feedback loops that make writing good tests the path of least resistance, and you'll set the standards for what "well-tested" means at Baseten. RESPONSIBILITIES Own Baseten's testing strategy end to end — define the standards, the tiers, and the tooling that engineering teams build against. Build and maintain unit, integration, load and performance testing frameworks Design end to end test infrastructure that provisions realistic dependencies

ABOUT BASETEN Baseten powers mission-critical inference for the world's most dynamic AI companies, like Cursor, Notion, OpenEvidence, Abridge, Clay, Gamma and Writer. By uniting applied AI research, flexible infrastructure, and seamless developer tooling, we enable companies operating at the frontier of AI to bring cutting-edge models into production. We're growing quickly and recently raised our $1.5B Series F , led by Altimeter Capital, Conviction Partners, and Spark Capital. Join us and help build the platform engineers turn to to ship AI products. THE ROLE Baseten is seeking talented and experienced Software Engineers to join our Observability team within the Infrastructure organization. As an early member of the Observability Team, you will be pivotal in building and shaping the observability experience for our internal and external customers. By joining this team, you’ll have a direct impact on the reliability and operational excellence of Basetens product systems. As Baseten scales its infrastructure across different cloud providers and diverse hardware, the volume and complexity of operational data is growing by orders of magnitude. This team is responsible for building high-throughput ingest pipelines, cost-efficient storage, and agentic diagnostic tools to ensure that we can detect, diagnose, and resolve issues in minutes rather than hours, even as the systems they operate become more complex. RESPONSIBILITIES Design and build scalable telemetry ingest and storage pipelines for metrics, logs, and traces across Baseten’s multi-cloud infrastructure Own and evolve core observability platforms, driving migrations and architectural improvements that improve reliability, reduce cost, and scale with organizational growth Build instrumentation libraries, SDKs, and integrations that make it easy for engineering teams to emit high-quality telemetry from their services Drive alerting and SLO infrastructure that enables teams to define, monitor, and respond to reliabi

ABOUT BASETEN Baseten powers mission-critical inference for the world's most dynamic AI companies, like Cursor, Notion, OpenEvidence, Abridge, Clay, Gamma and Writer. By uniting applied AI research, flexible infrastructure, and seamless developer tooling, we enable companies operating at the frontier of AI to bring cutting-edge models into production. We're growing quickly and recently raised our $1.5B Series F , led by Altimeter Capital, Conviction Partners, and Spark Capital. Join us and help build the platform engineers turn to to ship AI products. THE ROLE Baseten is seeking talented and experienced Software Engineers to join our Platform team within the Infrastructure organization. As an early member of Baseten's Platform Team, you will be pivotal in building internal infrastructure to support our engineering organization. You will own the deployment platform, release pipelines, and rollout safety mechanisms that allow engineers across Baseten to deploy changes rapidly while minimizing operational risk. Our mission is to make production deployments fast, safe, and increasingly autonomous. If you are passionate about elegant solutions—like streamlined monorepos, lightning-fast CI pipelines, and thoughtfully designed shared libraries—you'll thrive at Baseten. RESPONSIBILITIES Design and build continuous deployment infrastructure that safely rolls out changes across dozens of Kubernetes clusters and global regions. Develop systems for progressive delivery, including canary releases, staged rollouts, and automated rollback. Improve engineering velocity by reducing friction in the release pipeline and automating manual operational workflows. Work with product and infrastructure teams to ensure their services are deployable, observable, and resilient at scale. Implement and evolve deployment methodologies such as GitOps, infrastructure-as-code, and progressive delivery patterns. Build systems that automatically evaluate deployment health using metrics, logs, traces,

ABOUT BASETEN Baseten powers mission-critical inference for the world's most dynamic AI companies, like Cursor, Notion, OpenEvidence, Abridge, Clay, Gamma and Writer. By uniting applied AI research, flexible infrastructure, and seamless developer tooling, we enable companies operating at the frontier of AI to bring cutting-edge models into production. We're growing quickly and recently raised our $1.5B Series F , led by Altimeter Capital, Conviction Partners, and Spark Capital. Join us and help build the platform engineers turn to to ship AI products. THE ROLE Baseten is building its own GPU infrastructure for large-scale inference. As we move into large scale, high-density NVIDIA systems, the hardest failures are intermittent, cross-layer, and difficult to prove: RoCE congestion, InfiniBand stalls, ECN/DCQCN mis-tuning, bad optics, RNIC issues, host kernel stalls, GPU driver problems, and workload symptoms that look like network problems, but are not. We are hiring a Lead Software Engineer to build a first-class observability and root-cause analysis system for GPU fabrics. This is a hard distributed systems problem, not a dashboarding problem. The system will collect high-volume signals from switches, hosts, active probes, and inference services; reduce and correlate them in real time; understand topology and service ownership; and produce actionable diagnosis while an incident is still unfolding. This role sits at the boundary between networking and inference software. RDMA data paths, GPUDirect transfers, prefill/decode disaggregation, KV cache movement, request routing, and workload backpressure can all create fabric symptoms or hide real fabric failures. The goal is to tell an operator, quickly and with evidence, whether an incident is caused by the fabric, host, NIC, GPU, RDMA path, scheduler, or serving layer — and what to do next. EXAMPLE INITIATIVES Real-time telemetry engine — Build the ingestion, reduction, storage, and query path for high-cardinality fab