Research Engineer, Post-Training Model Evaluations

About the Team The Personality & Model Behavior team, within OpenAI’s broader Personal AGI team conducts research on how to shape personalities and guide the behavior of models. We think about topics such as emotional intelligence, reasoning, and how models interact thoughtfully with users. We’re particularly interested in understanding how individual users want ChatGPT to behave, and creating personalized models that feel uniquely tailored to each user. We integrate this research into ChatGPT and other OpenAI products that are used by hundreds of millions of users. About the Role We're looking for individuals with strong ML engineering skills and research experience, especially with novel and highly capable models, and in areas like reinforcement learning and reward modeling. An ideal candidate is passionate about product-driven research. In this role, you will: Conduct research around personalization, personality, and model behavior by leveraging and developing tools such as synthetic data, reward modeling, and reinforcement learning. Build robust evaluations and model training pipelines to facilitate our research. Innovate new post-training methods. 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. You might thrive in this role if you: Have a deep understanding of machine learning and its applications. Have prior knowledge in training and optimizing models and building evaluations. Are willing to dive into large ML codebases to debug issues. Thrive in dynamic and technically complex environments. Have a track record of delivering innovative, out-of-the-box solutions to address real-world constraints. 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 o

About the Team The Personal AGI team is responsible for training and improving pre-trained models to be deployed into ChatGPT, the API, and potential future products. The team partners closely with research and product teams across the company, and conducts research as a final step to prepare for real world deployment to millions of users, ensuring that our models are safe, efficient, and reliable. About the Role As a Research Engineer / Scientist, you will research and develop improvements to our models. Our team works in research areas combining reinforcement learning and products. We're looking for individuals with strong ML engineering skills and research experience, especially with novel and highly capable models. An ideal candidate is passionate about product-driven research. 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: Own and pursue a research agenda to improve model capability and performance. Collaborate closely with the other research and product teams, allowing customers to optimize their own models. Build robust evaluations for tracking modeling improvements. Design, implement, test, and debug code across our research stack. You might thrive in this role if you: Have a deep understanding of machine learning and machine learning applications. Have a working knowledge of relevant models, and building evaluations for model capability improvement. Are comfortable diving into a large ML codebase to debug. Thrive in a dynamic and technically complex environment. 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

About the Team The Personalization-Memory team, within OpenAI's broader Personal AGI organization, is focused on developing agents that can learn from prior interactions in order to become more helpful and efficient over time. We build general-purpose memory and personalization capabilities that transfer across ChatGPT and other agentic products, and we collaborate with applied engineering on the product surfaces that allow users to interact with memory. About the Role As a Research Engineer / Research Scientist on the Personalization-Memory team, you will research and develop improvements to memory usage and personalization in OpenAI's frontier models. Our team works on reinforcement learning, dataset creation, evaluations, and other post-training methods. We partner closely with research and product teams across the company to realize the vision of a truly personalized ChatGPT. We're looking for individuals who have a background in frontier model post-training, are able to iterate quickly, and who are passionate about product-driven research. 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: Own and pursue a research agenda for improving memory use and personalization in frontier models. Build robust evaluations for tracking modeling improvements. Design, implement, test, and debug code across our research stack. Collaborate closely with the research and product teams to influence the shape of technical solutions in the product. You might thrive in this role if you: Are passionate about personalization and building personalized assistants. Have experience working with user signals and human data to turn feedback into reliable signals for training and evaluation. Have a deep understanding of frontier model post-training and machine learning applications. Value principled approaches and research craftsmanship. Are comfortable diving into a lar

About the Team The Personal AGI team is responsible for training and improving pre-trained models to be deployed into ChatGPT, the API, and potential future products. In the Model Experience team, we shape the default character and behavior of ChatGPT: how the model communicates, responds to users, uses its capabilities, and behaves across different contexts and languages. Our goal is to make every interaction with ChatGPT thoughtful, helpful, and trustworthy. We take an opinionated view of what good human–AI interaction should look like, then turn that vision into real model behavior through human data, evaluations, reward models, and post-training. Our work sits at the intersection of research, product, and model design. We partner closely with teams across OpenAI to conduct research and ensure our models are thoughtful, safe, reliable to serve millions of users. About the Role As a Research Engineer / Scientist, you will research and develop improvements to our models. Our team works in research areas combining reinforcement learning and products. We're looking for individuals with strong ML engineering skills and research experience, especially with novel and highly capable models. An ideal candidate is passionate about product-driven research and the quality of human-AI interaction. 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: Own and pursue a research agenda to improve model capability and performance. Collaborate closely with the other research and product teams, allowing customers to optimize their own models. Build robust evaluations for tracking modeling improvements. Design, implement, test, and debug code across our research stack. You might thrive in this role if you: Have a deep understanding of machine learning and machine learning applications. Have good judgment about model behavior and can communicate this judgment effec

About the Team The Proactivity Research team, within OpenAI’s broader Personal AGI team, is focused on making our models in ChatGPT and future potential products proactive in ways that are truly useful. We're laying the technical foundations for AI that can anticipate what users need in real time, adapt as their goals and preferences shift, and build a deeper, evolving understanding of the person it's helping. About the Role As a Research Engineer / Scientist, you will research and develop improvements to our models’ personalization and agentic capabilities. Our team works on reinforcement learning, dataset creation, evaluations, and other post-training methods. We partner closely with research and product teams across the company to realize the vision of a highly personalized, collaborative, and proactive assistant. We're looking for individuals with strong ML engineering skills and research experience, especially with novel and highly capable models. An ideal candidate is passionate about product-driven research. 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: Own and pursue a research agenda to improve the proactivity and ability of our models to further user goals. Build robust evaluations for tracking modeling improvements. Design, implement, test, and debug code across our research stack. Collaborate closely with the other research and product teams to influence the shape of technical solutions in the product You might thrive in this role if you: Have a deep understanding of machine learning and machine learning applications. Have a working knowledge of LLM post-training and evaluation approaches Are passionate about, or have experience thinking about, personalization and enabling users to achieve their goals Are comfortable diving into a large ML codebase to debug. Thrive in a dynamic and technically complex environment. About OpenAI

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