Research Scientist
Core
Conducting foundational research on interpretability mechanisms to understand, visualize, and steer large AI models.
Role type
Research Scientist (AI Interpretability)
Builds
Novel techniques for model understanding and production-ready tools for enterprise applications
Domain
Artificial Intelligence / Machine Learning Interpretability
Deliverable
production ML models
Required skills
PhD in ML/CS/Quantitative Science, Deep familiarity with large models, Python, PyTorch, Technical writing
Preferred skills
Leading research, Open-source contributions, Interpretability/alignment/safe model development experience, Startup environment experience
Technologies
PyTorch, Python
Responsibilities
Conduct original research in interpretability, Prototype techniques to visualize and manipulate internal model structures, Collaborate with engineering to turn research into production-ready tools, Share work through publications and open-source contributions, Help define research direction
Seniority
Senior, hands-on IC
