Researcher, Interpretability
OpenAI · San Francisco
CHECKED 35M AGO
Frontier labremote$380k–$500k
At a glance
Highlights
- Study internal representations of deep learning models at scale.
- Help ensure future powerful models remain safe as they grow.
- Engineer infrastructure for studying model internals at scale.
What they offer
- Equity
Ideal candidate
Curious, mission-driven researcher passionate about AI safety and understanding deep networks, energized by collaborative large-scale research toward safe AGI.
Requirements
- Ph.D. or research experience in computer science, machine learning, or related field
- Experience in AI safety, mechanistic interpretability, or related disciplines
- 2+ years of research engineering experience and proficiency in Python or similar languages
- Enthusiasm for long-term AI safety and technical paths to safe AGI
- Thrive working with large-scale AI systems
Lab profile
About OpenAI
Builds safe frontier AI models and products like ChatGPT for broad benefit.
What they build
- ChatGPT
- OpenAI API
- Frontier AI models
Known for
- Frontier-scale distributed ML training
- Massive GPU fleet and data center operations
- Exabyte-scale data lakes and streaming
- AI alignment and safety research
Key facts
- Operates one of the world's largest GPU fleets