Research Engineer in Interpretability

Job Summary

To support cutting-edge interpretability research, the full-time Research Engineer in Interpretability will build and maintain specialized inference and training infrastructure while resolving scaling bottlenecks and designing tools for rapid experimentation, primarily working onsite in San Francisco with potential for exceptional remote candidates.

Key responsibilities:

• Build and maintain specialized inference and training infrastructure for interpretability research
• Resolve scaling and efficiency bottlenecks through profiling and optimization in collaboration with peer teams
• Design tools and platforms that enable researchers to experiment rapidly without engineering barriers

Required qualifications:

• 5-10+ years of experience building software
• Proficiency in at least one programming language (e.g., Python, Rust, Go, Java) and productivity with Python
• Strong curiosity and ability to learn quickly in unfamiliar domains
• Experience optimizing performance in large-scale distributed systems
• Bachelor's degree or equivalent experience in a relevant field