Agent Post Training Jobs

About the Team The Agent Post-Training team creates the frontier agents OpenAI ships to the world. We are training the models behind our agents in Codex, ChatGPT, the API, and other frontier products: persistent, proactive intelligence that can operate computers, collaborate with people and other agents, and expand what people and organizations can imagine, attempt, and achieve. We define what the next generation of agents should be able to do, build the training signal that teaches those abilities, and run the experiments that make them real. Our work spans coding, tool use, computer use, multi-agent coordination, long-horizon execution, factuality, instruction following, calibrated reasoning, and taste. Our team is where new model capabilities get made. We build the data, environments, graders, training methods, and feedback loops that shape what OpenAI's next agents can do, then carry those capabilities through major training runs and into the products people use. About the Role As a member of Agent Post-Training, Connectors, you will teach models how to interface with the top professional software using code. You will help train agents to use code, APIs, tools, and structured integrations to operate across applications like Slack, Google Workspace, GitHub, Notion, Linear, Salesforce, and other core systems of work. You will help enable models to take useful actions across a user’s digital context: finding information, updating systems, coordinating work, generating artifacts, and completing multi-step workflows through the tools teams already use. You will train models to be supercharged by the world’s most important productivity and enterprise software, turning connected tools into a powerful action surface for our agents. You will work with researchers, engineers, product teams, infrastructure teams, and safety/alignment partners to decide what should go into major model runs, measure whether it worked, and ship improvements into products used by real people.

About the Team The Agent Post-Training team creates the frontier agents OpenAI ships to the world. We are training the models behind our agents in Codex, ChatGPT, the API, and other frontier products: persistent, proactive intelligence that can operate computers, collaborate with people and other agents, and expand what people and organizations can imagine, attempt, and achieve. We define what the next generation of agents should be able to do, build the training signal that teaches those abilities, and run the experiments that make them real. Our work spans coding, tool use, computer use, multi-agent coordination, long-horizon execution, factuality, instruction following, calibrated reasoning, and taste. Our team is where new model capabilities get made. We build the data, environments, graders, training methods, and feedback loops that shape what OpenAI's next agents can do, then carry those capabilities through major training runs and into the products people use. About the Role As a member of Agent Post-Training, you will improve the capabilities, reliability, and product fit of OpenAI's agentic models. You might own a research direction, build the infrastructure that makes large training runs faster and more trustworthy, create evals that reveal where models fail, or drive a capability from an idea through experimentation, integration, and launch. This role is intentionally broad. The strongest candidates are not defined by one method or subfield; they are people who can take an ambiguous capability problem and make progress across research, engineering, data, evals, and product. You should be excited to work on models that act in the world: writing and debugging code, using tools, calling functions, operating computers, collaborating with other agents, and completing valuable work on behalf of users. You will work with researchers, engineers, product teams, infrastructure teams, and safety/alignment partners to decide what should go into major model runs, meas

About the Team The Agent Post-Training team creates the frontier agents OpenAI ships to the world. We are training the models behind our agents in Codex, ChatGPT, the API, and other frontier products: persistent, proactive intelligence that can operate computers, collaborate with people and other agents, and expand what people and organizations can imagine, attempt, and achieve. We define what the next generation of agents should be able to do, build the training signal that teaches those abilities, and run the experiments that make them real. Our work spans coding, tool use, computer use, multi-agent coordination, long-horizon execution, factuality, instruction following, calibrated reasoning, and taste. Our team is where new model capabilities get made. We build the data, environments, graders, training methods, and feedback loops that shape what OpenAI's next agents can do, then carry those capabilities through major training runs and into the products people use. About the Role As a researcher working on Frontier Evals & Environments, you will help build north star model environments to drive progress towards safe AGI/ASI. Your work will directly guide the research programs of the most ambitious training runs happening at OpenAI. Some prior open-sourced evaluations built by researchers in this role include GDPval , SWE-bench Verified , MLE-bench , PaperBench , and SWE-Lancer . If you are interested in feeling firsthand the fast progress of our models, and steering them towards good outcomes, this is the role for you. You will work with researchers, engineers, product teams, infrastructure teams, and safety/alignment partners to decide what should go into major model runs, measure whether it worked, and ship improvements into products used by real people. This is a high-agency role for people who want their work to land directly in frontier models. In this role, you might Create ambitious RL environments to push our models to their limits, and measure frontie

About the Team The Agent Post-Training team creates the frontier agents OpenAI ships to the world. We are training the models behind our agents in Codex, ChatGPT, the API, and other frontier products: persistent, proactive intelligence that can operate computers, collaborate with people and other agents, and expand what people and organizations can imagine, attempt, and achieve. We define what the next generation of agents should be able to do, build the training signal that teaches those abilities, and run the experiments that make them real. Our work spans coding, tool use, computer use, multi-agent coordination, long-horizon execution, factuality, instruction following, calibrated reasoning, and taste. Our team builds the data, environments, graders, training methods, and feedback loops that shape what OpenAI’s next agents can do and what they are like to work with, then carries those improvements through major training runs and into products used by people every day. About the Role As a member of the Agent Post-training Personality team, you will help make OpenAI’s agents exceptional collaborators. You will study what makes an agent thoughtful, clear, perceptive, appropriately proactive, and genuinely easy to work with, then translate those insights into evals, training data, reward signals, and model improvements. We use “personality” to mean much more than writing style or general likability. It includes whether an agent understands what the user is trying to accomplish, communicates with good judgment, adapts to context, asks useful questions, handles disagreement honestly and takes initiative at the right moments. The goal is to create a strong, tasteful default that can adapt to different people and situations. This work combines behavioral research, product thinking, research and communication taste. You will collaborate with product teams, human experts, and researchers across post-training and pretraining to ensure that improvements survive the full trai

About the Team The Agent Post-Training team creates the frontier agents OpenAI ships to the world. We are training the models behind our agents in Codex, ChatGPT, the API, and other frontier products: persistent, proactive intelligence that can operate computers, collaborate with people and other agents, and expand what people and organizations can imagine, attempt, and achieve. We define what the next generation of agents should be able to do, build the training signal that teaches those abilities, and run the experiments that make them real. Our work spans coding, tool use, computer use, multi-agent coordination, long-horizon execution, factuality, instruction following, calibrated reasoning, and taste. Our team is where new model capabilities get made. We build the data, environments, graders, training methods, and feedback loops that shape what OpenAI's next agents can do, then carry those capabilities through major training runs and into the products people use. About the Role We believe that the final enabler for AGI is spending compute on context. As a Context Researcher on Agent Post-Training, you will scale compute spent on context. You will get to work in our frontier training stack on enabling the next paradigm of model training with a clear product interface for iterative deployment (Codex Chronicle). You will work with researchers, engineers, product teams, infrastructure teams, and safety/alignment partners to decide what should go into major model runs, measure whether it worked, and ship improvements into products used by real people. This is a high-agency role for people who want their work to land directly in frontier models. In this role, you might Design and run experiments that improve scaling of compute on context. Own end-to-end improvements to the post-training stack, including RL, data pipelines, graders, reward signals, evals, diagnostics, and model-behavior analysis. Build evals and environments that expose the next set of model failures,

About the Team The Agent Post-Training team creates the frontier agents OpenAI ships to the world. We are training the models behind our agents in Codex, ChatGPT, the API, and other frontier products: persistent, proactive intelligence that can operate computers, collaborate with people and other agents, and expand what people and organizations can imagine, attempt, and achieve. We define what the next generation of agents should be able to do, build the training signal that teaches those abilities, and run the experiments that make them real. Our work spans coding, tool use, computer use, multi-agent coordination, long-horizon execution, factuality, instruction following, calibrated reasoning, and taste. Our team is where new model capabilities get made. We build the data, environments, graders, training methods, and feedback loops that shape what OpenAI's next agents can do, then carry those capabilities through major training runs and into the products people use. About the Role As a member of this API & power-users team, you will improve the capabilities, reliability, and product fit of OpenAI’s agentic models for power users and API developers. You might design evals from real developer workflows, build training environments around production-like tool use, turn qualitative model failures into training data, evals, or post-training interventions, or drive a behavior improvement from discovery through post-training, integration, and launch. This role is intentionally broad. The strongest candidates are comfortable turning ambiguous model behavior problems into concrete progress, whether that means improving tool use, planning, instruction following, recovery from mistakes, or how models behave in API-based workflows. You should be excited to work across research, engineering, data, evals, and product to make models better at acting in real workflows. You will work closely with researchers, engineers, API/product teams, Codex, infrastructure, and safety/align

About the Team The Agent Post-Training team creates the frontier agents OpenAI ships to the world. We are training the models behind our agents in Codex, ChatGPT, the API, and other frontier products: persistent, proactive intelligence that can operate computers, collaborate with people and other agents, and expand what people and organizations can imagine, attempt, and achieve. We define what the next generation of agents should be able to do, build the training signal that teaches those abilities, and run the experiments that make them real. Our work spans coding, tool use, computer use, multi-agent coordination, long-horizon execution, factuality, instruction following, calibrated reasoning, and taste. Our team is where new model capabilities get made. We build the data, environments, graders, training methods, and feedback loops that shape what OpenAI's next agents can do, then carry those capabilities through major training runs and into the products people use. About the Role As a member of Agent Post-Training, Computer Use, you will teach models to operate computers. You will help train models that can navigate browsers and desktops, use tools and applications, reason through complex workflows, collaborate with users and other agents, and complete long-horizon tasks with reliability and judgment. This work sits at the intersection of frontier model training, product behavior, evaluation, and systems engineering, and will directly shape the computer-use capabilities shipped in OpenAI’s next generation of agents. Currently, our models are the best in the world at this behavior! You will work with researchers, engineers, product teams, infrastructure teams, and safety/alignment partners to decide what should go into major model runs, measure whether it worked, and ship improvements into products used by real people. This is a high-agency role for people who want their work to land directly in frontier models. In this role, you might Design and run experiments th

About the Team The Agent Post-Training team creates the frontier agents OpenAI ships to the world. We are training the models behind our agents in Codex, ChatGPT, the API, and other frontier products: persistent, proactive intelligence that can operate computers, collaborate with people and other agents, and expand what people and organizations can imagine, attempt, and achieve. We define what the next generation of agents should be able to do, build the training signal that teaches those abilities, and run the experiments that make them real. Our work spans coding, tool use, computer use, multi-agent coordination, long-horizon execution, factuality, instruction following, calibrated reasoning, and taste. Our team is where new model capabilities get made. We build the data, environments, graders, training methods, and feedback loops that shape what OpenAI's next agents can do, then carry those capabilities through major training runs and into the products people use. About the Role As a member of Agent Post-Training, Artifacts, you will train frontier models to create polished, useful work products: documents, spreadsheets, slide decks, dashboards, reports, analyses, and other interactive or editable artifacts. You will help teach our models to move from a vague user goal to a finished artifact with strong structure, visual taste, domain judgment, correctness, and low latency. This work will require owning improvements across our post-training stack, including RL, data pipelines, graders, reward signals, evals, and behavioral analysis. You will work with researchers, engineers, product teams, infrastructure teams, and safety/alignment partners to decide what should go into major model runs, measure whether it worked, and ship improvements into products used by real people. This is a high-agency role for people who want their work to land directly in frontier models. In this role, you will: Design and run experiments that improve agentic model behavior for complex so

About the team The Agent Post-Training team creates the frontier agents OpenAI ships to the world. We are training the models behind our agents in Codex, ChatGPT, the API, and other frontier products: persistent, proactive intelligence that can operate computers, collaborate with people and other agents, and expand what people and organizations can imagine, attempt, and achieve. We define what the next generation of agents should be able to do, build the training signal that teaches those abilities, and run the experiments that make them real. Our work spans coding, tool use, computer use, multi-agent coordination, long-horizon execution, factuality, instruction following, calibrated reasoning, and taste. Our team is where new model capabilities get made. We build the data, environments, graders, training methods, and feedback loops that shape what OpenAI's next agents can do, then carry those capabilities through major training runs and into the products people use. About the Role As a researcher working on Frontier Evals & Environments, you will help build north star model environments to drive progress towards safe AGI/ASI. Your work will directly guide the research programs of the most ambitious training runs happening at OpenAI. Some prior open-sourced evaluations built by researchers in this role include GDPval , SWE-bench Verified , MLE-bench , PaperBench , and SWE-Lancer . If you are interested in feeling firsthand the fast progress of our models, and steering them towards good outcomes, this is the role for you. You will work with researchers, engineers, product teams, infrastructure teams, and safety/alignment partners to decide what should go into major model runs, measure whether it worked, and ship improvements into products used by real people. This is a high-agency role for people who want their work to land directly in frontier models. In this role, you'll: Create ambitious RL environments to push our models to their limits, and measure frontier

Scale Labs, Research Scientist — Safety Post Training As the leading data and evaluation partner for frontier AI companies, Scale plays an integral role in understanding the capabilities and safeguarding AI models and systems. Building on this expertise, Scale Labs has launched a new team focused on policy research, to bridge the gap between AI research and global policymakers to make informed, scientific decisions about AI risks and capabilities. Our research tackles the hardest problems in agent robustness, AI control protocols, and AI risk evaluations to help governments, industry, and the public understand and mitigate AI risk while maximizing AI adoption. This team collaborates broadly across industry, the public sector, and academia and regularly publishes our findings. We are actively seeking talented researchers to join us in shaping this vision. As a Research Scientist working on Safety Post-Training you will develop and apply post-training methods and interpretability techniques to make frontier AI systems safer, and better understood by researchers and policymakers.. For example, you might: Design and run post-training pipelines to study how training choices affect model safety, robustness, and alignment properties; Develop interpretability-informed evaluations that reveal how and why models produce unsafe, deceptive, or otherwise undesirable behaviors, and use those insights to guide targeted mitigations; Collaborate with policymakers, engineers, and other researchers to translate post-training and interpretability findings into actionable safety standards, evaluation benchmarks, and best practices. Ideally you’d have: Commitment to our mission of promoting safe, secure, and trustworthy AI deployments in the industry as frontier AI capabilities continue to advance. Experience with post-training and RL techniques such as RLHF, DPO, GRPO, and similar approaches. A track record of published research in machine learning, particularly in generati

About the Team The Agent Safety team works to ensure that increasingly capable AI agents act safely, exercise sound judgment, and remain aligned with user intent. Our mission is to reduce the probability of severe unintended outcomes from increasingly capable AI agents while preserving their ability to act effectively and autonomously. Our work spans three areas: Training: Create training methods, environments and data that teach agents to make better decisions in consequential situations. We turn real-world failures into training signals that prevent similar incidents, and identify precursor behaviors and mitigations to address emerging risks. Measurements: Build evaluations and production metrics that identify emerging risks and measure whether our interventions work. Oversight: Develop oversight and system mitigation mechanisms that reduce harmful actions while preserving useful autonomy (for example future versions of auto-review ). About the Role We’re looking for strong executors with excellent judgment, comfort with ambiguity, and an understanding of frontier model research. You don’t need prior safety or alignment experience, we also welcome people that recently realized that alignment and safety is a critical area to contribute to. This role is based in San Francisco, CA. We use a hybrid work model of 3 days in the office per week and offer relocation assistance to new employees. In this role, you will: Train and evaluate frontier models to reduce harmful or misaligned agent actions, forming clear hypotheses and executing independently through ambiguity. Mine incidents and build scalable measurement, data-processing, and evaluation systems that turn real failures into repeatable safety signals. Collaborate closely with post-training, capabilities, oversight, and pre-training partners to ship research-backed mitigations into large-scale training and agent systems. You might thrive in this role if you: Have demonstrated strength in research engineering, ML en

Airbnb was born in 2007 when two hosts welcomed three guests to their San Francisco home, and has since grown to over 5 million hosts who have welcomed over 2 billion guest arrivals in almost every country across the globe. Every day, hosts offer unique stays and experiences that make it possible for guests to connect with communities in a more authentic way. The Community You Will Join: Machine Learning and Artificial Intelligence are at the heart of the Airbnb product. From Trust to Payments, and from Customer Service to Marketing we rely on ML to ensure that guests and hosts have the best possible experience with Airbnb. The CS AI product team is responsible for driving CSxAI (Customer Support x Artificial Intelligence) initiatives by adopting the Generative AI technologies to enable an intelligent, scalable and exceptional service experience. The team develops and enhances various AI models, ML services and tools including LLM fine-tuning, alignment and optimization, RAG/Search, LLM evaluation and testing automation, feedback-based learning and guardrail for a wide range of applications in Airbnb. The Difference You Will Make: As a senior staff machine learning engineer, you will be responsible for fine-tuning state-of-the-art LLMs for diverse use cases while optimizing models for high-performance deployment on Airbnb’s ML Infrastructure. You will partner with product managers, software engineers, data scientists and operation teams to brainstorm, design and develop AI products such as AI Assistant, Autonomous agent, recommendation, travel planning, and many more products that make meaningful impacts in the world of travel. A Typical Day: Work with large scale structured and unstructured data; explore, experiment, build and continuously improve foundation models for Airbnb product, business and operational use cases. Create a multi-year tech roadmap that enables our team to stay on the leading edge of the rapidly evolving AI landscape and

About the Team The Post-Training Frontiers team is responsible for training the frontier agents OpenAI ships to the world (GPT-Next). We train the flagship agentic models behind Codex, ChatGPT, and the API through large-scale reinforcement learning. The team’s work spans four areas. First, execution and science: working with teams across OpenAI to decide what can go into the final model and how, using scientific experiments and evals that are representative of the final pipeline so issues can be recognized early. Second, RL scaling: executing the final large-scale reinforcement learning run, making sure GPUs are used efficiently and training stays healthy. Third, research: improving horizontal capabilities like instruction following, factuality, memory, and multi-agent behavior, where the team’s broad visibility helps identify cross-cutting improvements across teams and domains. Fourth, engineering: maintaining the infrastructure stack and internal tools to ensure that both the final run and all integrations go as smoothly as possible and that the systems are easy to work with. About the Role This role focuses on keeping our frontier RL training runs fast, reliable, and unblocked. You will work across engineering and infrastructure problems as they emerge, from scaling and orchestration issues to inference bottlenecks, numerical problems, and hardware failures, as well as supporting large horizontal integrations in the big run, like multi-agent capabilities or memory. This is a role for a strong generalist who quickly learns anything needed for the task, has high attention to detail, debugs deeply, and is motivated by fixing the highest-impact problem in front of the team. In this role, you will: Keep large-scale async RL training runs moving by jumping into the most urgent engineering and infrastructure problems. Debug issues across training systems, inference, orchestration, scaling, and distributed infrastructure. Improve the reliability and efficiency of RL trai

About the Team The Future of Computing Research team is an applied research team within the Consumer Devices group focused on developing new methods, models, and evaluation frameworks that support our vision for the future of computing. We work at the frontier of multimodal AI, helping turn emerging model capabilities into product experiences that are useful, delightful, and worthy of long-term trust. Our work explores a new class of AI systems that can learn over time, adapt to individuals, and support people in the flow of daily life. This includes long-term memory, user modeling, and personalization systems that are aligned not just with immediate satisfaction, but with a person’s broader goals, values, and well-being. We work closely across research, engineering, design, product, and safety to define what it means to build AI systems that know you over time, act at the right moment, and help in ways that are context-aware, respectful, and demonstrably beneficial. About the Role We are looking for a Research Engineer / Scientist to join the Future of Computing Research team to work on RLHF and post-training for personalized, multimodal AI systems. This role will focus on building the learning and evaluation foundations that help models become more context-aware, adaptive, and useful over time. You will work on problems such as reward modeling, preference learning, long-horizon evaluation, and policy improvement for systems that must make high-quality behavioral decisions in realistic user settings. The work is deeply product-grounded: success is not just higher benchmark performance, but better model behavior in real-world use. The ideal candidate is excited about pushing beyond one-turn assistant behavior toward systems that improve through feedback, learn from richer signals, and are trained against meaningful notions of user value. Internally, that maps closely to the need for careful reward design, feedback loops, and evaluation frameworks that test whether i

About Ema Ema is building the world’s leading Agentic AI platform to transform enterprise productivity. We enable organizations to delegate repetitive tasks to Ema, the Universal AI Employee, delivering 10x gains in workforce efficiency, across functions. Founded by former executives from Google, Coinbase, Flipkart, and Okta, our team includes engineers from premier tech companies and graduates of Stanford, MIT, UC Berkeley, CMU, and IITs. We are backed by industry leading investors including Accel, Naspers/Prosus, Section32, and angels like Sheryl Sandberg and Dustin Moskovitz. Headquartered in Silicon Valley and with offices in London, Bangalore and Vancouver, Ema is at the frontier of what Agentic AI can do in production — we ship real systems that run real business processes at scale. The residency You own one hard problem end to end. You write the proposal, build the system, design the evaluation, ship behind a gate, and finish with a write-up of what turned out to be true, including the parts that didn't work. You'll sit in the production codebase with a senior mentor and real production data. Recent residents have shipped self-improving harnesses, inference-cost work, agent memory, and eval infrastructure. Your project gets scoped with you, not handed to you. The problem space The loop we care about: production traces become data, data becomes training and evaluation, and better agents produce better traces. Projects live somewhere on that loop. Harness and inference-time work. Context engineering, tool and skill design, orchestration, and deciding where extra inference compute actually pays. Self-improvement loops run behind hard fences. Post-training for agents. SFT on curated trajectories, preference optimization, RL on real agent tasks. Reward design where outcomes are verifiable, process vs. outcome supervision, distilling frontier behavior into cheaper models. Environments and rewards. Turning enterprise workflows into training and eval environments: fi