Software Engineer, Model Inference

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 the Team Our team analyzes inference stack performance across the application, model, and fleet layers to identify bottlenecks and drive faster, cheaper inference. We combine systems profiling, benchmarking, and analysis to understand where time and cost are spent, then turn that understanding into performance optimizations and models that project performance and capacity needs for future launches. About the Role In this role, you will model inference performance across application, model, and fleet layers with higher fidelity. You will build cost-to-serve estimates from microbenchmarks and create tools that help cross-functional teams reason about latency, capacity, utilization, and cost tradeoffs. In this role, you will Build and refine performance models that translate microbenchmark results into cost-to-serve estimates. Analyze inference workloads end to end across applications, models, and fleet infrastructure. Enhance tooling to identify bottlenecks across layers for latency and throughput. Partner with other teams to turn performance insights into concrete improvements and project how future changes affect inference. You might thrive in this role if you: Enjoy reasoning from first principles about distributed systems, model inference, and hardware efficiency. Are comfortable working across abstraction layers, from application behavior to kernels, accelerators, networking, and fleet scheduling. Have deep expertise with performance profiling, benchmarking, analysis, and optimization. Enjoy collaborating with engineering and research teams to improve real production systems. About OpenAI OpenAI is an AI research and deployment company dedicated to ensuring that general-purpose artificial intelligence benefits all of humanity. We push the boundaries of the capabilities of AI systems and seek to safely deploy them to the world through our products. AI is an extremely powerful tool that must be created with safety and human needs at its core, and to achieve o

About the Team The GPT Infrastructure team builds systems that turn advances in model inference and optimization into reliable production capabilities. We enable OpenAI workloads to be qualified and optimized across new accelerator platforms without requiring a one-off port and tuning effort for every hardware target. Our work spans distributed systems, model execution, compilers and runtimes, performance engineering, secure partner integrations, evaluation systems, and developer tooling. We build the infrastructure that makes optimization workflows automated, reproducible, and trustworthy. About the Role We are seeking a software engineer to help build the platform that qualifies and optimizes inference workloads across heterogeneous compute environments. You will develop both OpenAI-hosted services and secure partner-side software for running long-lived optimization workflows. These workflows generate candidate kernels, runtime configurations, and serving-stack changes; compile and execute them on target hardware; verify their correctness; measure their performance; and use the results to guide further optimization. You will work across model architecture, distributed execution, compilers, runtimes, networking, and accelerator systems. A central part of the role is turning research prototypes and one-off hardware bring-up efforts into reliable, reusable infrastructure with clear contracts, reproducible results, strong observability, and well-defined security boundaries. Key Responsibilities Design, build, and operate APIs and control-plane services for long-running workload qualification and optimization campaigns, including scheduling, retries, checkpointing, resource budgets, and observability. Build secure partner-side execution and evaluation software that can compile, run, verify, profile, and benchmark candidate artifacts on accelerator hardware. Integrate model workloads, hardware profiles, compiler toolchains, runtimes, serving engines, and distributed-exe

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 Product Engineer on the Dedicated Inference team, you'll shape the state-of-the-art developer experience for deploying and operating AI workloads in production. From the CLI and SDKs to APIs, observability, and debugging workflows, you'll build the tools customers rely on every day to manage mission-critical inference deployments. Few teams at Baseten have as much breadth and visibility as Dedicated Inference. The team is often at the forefront of new product development, giving engineers the opportunity to shape the experience of some of our most important customers. EXAMPLE INITIATIVES You'll get to work on these types of projects as part of our Dedicated Inference team: Chains for multi-component workflows Asynchronous inference Model APIs for frontier models Model training built for production inference RESPONSIBILITIES Implement new features and products for the team Design ergonomic APIs and abstractions to solve customer problems Fix bugs and resolve customer issues with urgency Work across the stack - regardless of where you start, you’ll end up touching both React Components and Kubernetes Pods Work closely with the product and forward deployed engineering teams to develop and drive new product ideas REQUIREMENTS Bachelor's degree or higher in Computer Science or related field Proficient coding abilities in one or more popular programming or scripting languages; Python, Go, or Javascript proficie

About the Team Compute Foundations builds the software that manages OpenAI’s GPU compute infrastructure across sites, data centers, and infrastructure providers, supporting model training and inference. Our systems turn large, heterogeneous fleets of machines into dependable compute for research and products. We build Kubernetes-based control planes, controllers, services, and APIs that coordinate the lifecycle of machines and clusters. We connect global infrastructure management with the realities of bare-metal systems, giving clients consistent interfaces across differences in hardware, topology, and provider behavior. About the Role You will build distributed systems that provision, configure, and manage compute throughout its lifecycle. Your work will connect global services and Kubernetes controllers with the systems that bring machines online, update them safely, and recover them when something goes wrong. This role combines software architecture with an understanding of how machines and data centers work. You might design a lifecycle API, improve controller performance under high concurrency and provider rate limits, or trace a provisioning failure from an API through reconciliation to network boot or host configuration. You will help these systems remain reliable as the fleet expands across sites and generations of GPU hardware. We value depth in relevant systems and the ability to connect layers. You do not need to arrive as an expert in every component of the stack. In this role, you will: Design, build, and operate Kubernetes-based controllers and distributed services that coordinate infrastructure across sites, isolate failures, and scale as GPU capacity grows. Define APIs and resource models that let clients request and track lifecycle operations through consistent interfaces across hardware platforms and providers. Build provisioning and configuration services that coordinate network boot, hardware management interfaces, and the deployment of firmware,

About the Team The Hardware Health and Observability team owns the end-to-end health lifecycle of OpenAI’s global compute fleet. Our mission is to maximize healthy, usable compute across accelerator vendors, generations, cloud providers, and regions through reliable health signals, automated remediation, and scalable operational tooling. We build the systems that observe, detect, remediate, and verify hardware issues across GPUs, CPUs, networking, and platform infrastructure, enabling frontier model training and inference workloads to run reliably at hyperscale. We are the last line of defense for the success of OAI’s production and research workloads. About the Role On the Hardware Health and Observability team, you’ll build critical infrastructure that keeps OpenAI’s largest compute clusters healthy and operational at scale. Even small numbers of unhealthy systems can impact large-scale training and inference workloads. This team focuses on minimizing downtime, improving fleet efficiency, and ensuring compute resources remain continuously available to researchers and product teams. Engineers on this team own problems end-to-end, from defining health signals and debugging failures to building automated remediation systems that operate across millions of GPUs globally. In this role, you will: Define and maintain health signals across GPUs, CPUs, networking, and platform infrastructure. Build and evolve health checks that detect, remediate, and verify failures at scale. Ensure critical health checks execute with minimal latency to maximize workload uptime. Investigate hardware failures and system-level issues across large-scale compute environments. Own node lifecycle workflows including drain, quarantine, repair, RMA, and return-to-service processes. Build automation and tooling that enables global cluster management with minimal manual intervention. Partner with workload, reliability, and provider teams to integrate health signals into training and inference system