openai
Research Engineer / Research Scientist- Personal AGI (Post Training)
San Franciscofulltimemid
About this role
Join OpenAI's Post-Training team to research and develop improvements for large language models deployed in ChatGPT and the API. You'll combine reinforcement learning with product-driven research to enhance model capability, safety, and reliability for millions of users.
What you'll do
- Own and pursue a research agenda to improve model capability and performance
- Collaborate with research and product teams to optimize model deployment
- Build robust evaluation frameworks for tracking modeling improvements
- Design, implement, test, and debug code across the research stack
- Prepare models for real-world deployment ensuring safety and efficiency
What they're looking for
- Machine learning fundamentals and applications
- Reinforcement learning
- ML model evaluation and benchmarking
- Large codebase debugging and navigation
- ML engineering and implementation
- Python or similar programming languages
- Knowledge of modern language models
Benefits
- Hybrid work model (3 days in office per week)
- Based in San Francisco, CA
- Relocation assistance for new employees
- Work on cutting-edge AI systems
- Collaboration with leading AI research teams
Opens the official application on the employer’s site. No login required.