Research Engineer, Interpretability
Core
Build and maintain specialized inference and training infrastructure to reverse-engineer neural networks for AI safety and interpretability research.
Role type
Senior IC research engineer (ML infrastructure)
Builds
Instrumented forward/backward passes, activation extraction pipelines, and steering vector application tools for large-scale LLMs
Domain
Artificial Intelligence / Machine Learning Safety
Deliverable
production ML models
Required skills
Python, distributed systems, profiling, optimization, PyTorch, CUDA, JAX, XLA, GPU/TPU optimization
Preferred skills
Large-scale distributed systems optimization, transformer architecture fundamentals, high-performance LLM inference, research tooling development
Technologies
Python, Rust, Go, Java, PyTorch, CUDA, JAX, XLA, GPUs, TPUs
Responsibilities
Build and maintain specialized inference and training infrastructure; Resolve scaling and efficiency bottlenecks through profiling and optimization; Design tools and platforms for rapid researcher experimentation; Support production safety audits with high reliability; Work across the stack from model internals to user-facing tooling
Seniority
Senior, hands-on IC
