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 ambiguous problems into clear results.
- Collaborate effectively across the full stack, including systems, data, model training, evaluations, and other research teams.
- Are comfortable building and maintaining the data pipelines, tooling, and infrastructure needed to support emerging AI capabilities.
- Are comfortable working on problems without clear definitions or established playbooks.
- Think rigorously about scientific quality, research taste, safety, privacy, reliability, performance, and scale.
- Are excited about using increasingly capable AI systems to accelerate meaningful research.
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.