Researcher, Recursive Self-Improvement Safety

About the Team The Recursive Self-Improvement (RSI) team works across research, engineering, product, and infrastructure to build AI systems that accelerate and ultimately conduct high-quality research at OpenAI. We work to automate real research workflows and improve research productivity by building systems and feedback loops, designing evaluations, and training models to develop missing capabilities. Our work spans the full lifecycle of model training, evaluation, and deployment to help researchers move faster and tackle increasingly ambitious problems. About the Role We’re hiring research scientists , research engineers , and AI systems engineers to work on automating research at OpenAI. This role is based in San Francisco, CA. In this role, you will: Design evaluations for research judgment, hypothesis generation and testing, and long-horizon experiment execution. Turn real research workflows and model failures into data and evaluation flywheels. Improve model research capabilities through agent harnesses, synthetic data, RL environments, and model training. Build and maintain safe, reliable integrations between our models and OpenAI’s research infrastructure. Develop research agents, experiment-orchestration systems, and sandboxed runtimes that support real research workflows. Create metrics and economic models to understand RSI’s current and future effects on research productivity, model capabilities, and the safety of internal deployments. This is a high-ownership role for researchers and engineers who thrive in ambiguity, move fluidly between research and implementation, and turn emerging opportunities into rigorous, reliable, scalable results. You might thrive in this role if you: Have research or engineering experience across LLM training, model evaluations, agent systems, synthetic data, research infrastructure, or large-scale distributed systems. Are a strong generalist who can move between open-ended research and practical implementation, turning ambig

About the Team The Safety Training research team aims to fundamentally advance our capabilities for precisely implementing safe behavior in AI models, and to leverage these advances to make OpenAI’s deployed models safe and beneficial. This requires a breadth of new ML research to address the growing set of safety challenges as AI becomes more powerful and used in more settings. Key focus areas include how to train nuanced safety behaviors, how to make the model robust to bad actors, how to address privacy and security risks, and how to make the model trustworthy in safety-critical situations. We seek to learn from deployment and distribute the benefits of AI, while ensuring that this powerful tool is used responsibly and safely. About the Role We’re seeking a researcher to train and evaluate models for U.S. government use, with a focus on national security applications. You’ll advance safety post-training and robustness, helping models follow nuanced policies while preserving their usefulness and capabilities. In this role, you will: Research and implement methods for safety training, reinforcement learning, and adversarial robustness. Develop evaluations, identify model failure modes, and use findings to improve training. Work with research, engineering, security, and policy partners to support safe, reliable deployment. You might thrive in this role if you: Bring 4+ years of relevant AI safety research experience, including RLHF, adversarial training, or robustness. Have a degree in computer science, machine learning, or a related field, and strong deep learning research or engineering skills. Have experience improving model safety for deployment and enjoy collaborative research. Are motivated by OpenAI’s mission and the responsible use of AI in safety-critical settings. Security Requirements Active TS/SCI clearance or equivalent. About OpenAI OpenAI is an AI research and deployment company dedicated to ensuring that general-purpose artificial intelligence benefi

About the Team The Interpretability team studies internal representations of deep learning models. We are interested in using representations to understand model behavior, and in engineering models to have more understandable representations. We are particularly interested in applying our understanding to ensure the alignment of powerful AI systems. Our working style is collaborative and curiosity-driven. About the Role OpenAI is seeking a researcher passionate about understanding deep networks, with a strong background in engineering, quantitative reasoning, and the research process. You will develop and carry out a research plan in mechanistic interpretability, in close collaboration with a highly motivated team. You will play a critical role in helping OpenAI ensure future models remain safe even as they grow in capability. This will make a significant impact on our goal of building and deploying safe AGI. In this role, you will: Develop and publish research on techniques for understanding representations of deep networks. Engineer infrastructure for studying model internals at scale. Collaborate across teams to work on projects that OpenAI is uniquely suited to pursue. Guide research directions toward demonstrable usefulness and/or long-term scalability. You might thrive in this role if you: Are excited about OpenAI’s mission of ensuring AGI benefits all of humanity, and are aligned with OpenAI’s charter . Show enthusiasm for long-term AI safety & alignment, and have thought deeply about technical paths to safe AGI. Bring experience in the field of AI safety & alignment, mechanistic interpretability, or spiritually related disciplines. Hold a Ph.D. or have research experience in computer science, machine learning, or a related field. Thrive in environments involving large-scale AI systems, and are excited to make use of OpenAI’s unique resources in this area. Possess 2+ years of research engineering experience and proficiency in Python or similar languag

About the Team Models are becoming increasingly capable—moving from tools that assist humans to agents that can plan, execute, and adapt in the real world. Mitigating the frontier risks resulting from these capabilities is paramount to OpenAI’s ability to continue deploying models safely. The Preparedness team is dedicated to addressing these critical risks. Our work includes: Measurement. Monitoring and predicting the evolving capabilities of frontier AI systems. Mitigation. Keeping misuse and misalignment safeguards, alignment tools, and security measures on track to adequately address extreme threats that might arise in the future. Coordination. Setting mitigation targets by maintaining OpenAI’s preparedness framework , and partnering with other staff to achieve these targets. This is urgent, fast-paced work that has far-reaching implications for the company and for society. About the Role We are seeking exceptional researchers who can push the frontier of safety mitigations. You will help derisk frontier models by developing novel safety mitigations, developing and applying new techniques from domains like interpretability, control, and alignment to ensure the safety of OpenAI’s deployed models. You will play a critical role in defining how a safe AI system should look in the future at OpenAI, making a significant impact on our mission to build and deploy safe AGI. This role requires strong technical depth and close cross-functional collaboration to ensure our safety mitigations are enforceable, scalable, and effective. We seek researchers who can partner with experts across domains such as misalignment, cybersecurity, and biology in order to develop the best possible end-to-end safety stack. In this role, you will: Work on identifying emerging AI safety risks and new methodologies for exploring and mitigating the impact of such risks Build (and then continuously refine) the evaluations that enable us to assess the extent of these risks; this might include worki

About the Team The Interpretability team studies internal representations of deep learning models. We are interested in using representations to understand model behavior, and in engineering models to have more understandable representations. We are particularly interested in applying our understanding to ensure the safety of powerful AI systems. Our working style is collaborative and curiosity-driven. About the Role OpenAI is seeking a researcher passionate about understanding deep networks, with a strong background in engineering, quantitative reasoning, and the research process. You will develop and carry out a research plan in mechanistic interpretability, in close collaboration with a highly motivated team. You will play a critical role in helping OpenAI ensure future models remain safe even as they grow in capability. This will make a significant impact on our goal of building and deploying safe AGI. In this role, you will: Develop and publish research on techniques for understanding representations of deep networks. Engineer infrastructure for studying model internals at scale. Collaborate across teams to work on projects that OpenAI is uniquely suited to pursue. Guide research directions toward demonstrable usefulness and/or long-term scalability. You might thrive in this role if you: Are excited about OpenAI’s mission of ensuring AGI benefits all of humanity, and are aligned with OpenAI’s charter . Show enthusiasm for long-term AI safety, and have thought deeply about technical paths to safe AGI. Bring experience in the field of AI safety, mechanistic interpretability, or spiritually related disciplines. Hold a Ph.D. or have research experience in computer science, machine learning, or a related field. Thrive in environments involving large-scale AI systems, and are excited to make use of OpenAI’s unique resources in this area. Possess 2+ years of research engineering experience and proficiency in Python or similar languages. Are deeply curious. About OpenA

About the Team The Safety Systems team is responsible for various safety work to ensure our best models can be safely deployed to the real world to benefit the society, and is at the forefront of OpenAI's mission to build and deploy safe AGI, driving our commitment to AI safety and fostering a culture of trust and transparency. The Safety Oversight Research team aims to fundamentally advance our capabilities to maintain oversight over frontier AI models, and leverage these advances to ensure OpenAI’s deployed models are safe and beneficial. This requires a breadth of new ML research in the areas of human-AI collaboration, reasoning, robustness, and scalable oversight to keep pace with model capabilities. We invest heavily in developing novel model and system-level methods of identifying and mitigating AI misuse and misalignment. Our goal is to learn from deployment and distribute the benefits of AI, while ensuring that this powerful tool is used responsibly and safely. About the Role OpenAI is seeking a senior researcher with a passion for AI safety and experience in safety research. Your role will set directions for research to maintain effective oversight of safe AGI and work on research projects to identify and mitigate misuse and misalignment in our AI systems. You will play a critical role in defining how a safe AI system should look in the future at OpenAI, making a significant impact on our mission to build and deploy safe AGI. In this role, you will: Develop and refine AI monitor models to detect and mitigate known and emerging patterns of misuse and misalignment. Set research directions and strategies to make our AI systems safer, more aligned, and more robust. Evaluate and design effective red-teaming pipelines to examine the end-to-end robustness of our safety systems, and identify areas for future improvement. Conduct research to improve models’ ability to reason about questions of human values, and apply these improved models to practical safety challen