Research Engineer, Interpretability na Anthropic

Presencial - San Francisco, CA

Candidatar-se
Ver mais vagas na Anthropic

Anthropic’s Interpretability team is seeking a Research Engineer to build and maintain specialized inference and training infrastructure for interpretability research. The role involves resolving scaling and efficiency bottlenecks, designing tools and platforms for rapid experimentation, and helping bring interpretability research into production safety audits. The position is based in San Francisco but may consider remote work for exceptional candidates.

Requirements

Skills

  • 5-10+ years of experience building software
  • Highly proficient in at least one programming language (e.g., Python, Rust, Go, Java) and productive with Python
  • Extremely curious about unfamiliar domains; can quickly learn and put that knowledge to work, e.g., diving into new layers of the stack to find bottlenecks
  • Strong ability to prioritize the most impactful work and comfortable operating with ambiguity and questioning assumptions
  • Prefer fast-moving collaborative projects to extensive solo efforts
  • Curious about interpretability research and its role in AI safety (though no research experience is required!)
  • Care about the societal impacts and ethics of your work
  • Comfortable working closely with researchers, translating research needs into engineering solutions
  • Optimizing the performance of large-scale distributed systems
  • Language modeling fundamentals with transformers
  • High Performance LLM optimization: memory management, compute efficiency, parallelism strategies, inference throughput optimization
  • Working hands-on in a mainstream ML stack - PyTorch/CUDA on GPUs or JAX/XLA on TPUs
  • Collaborating closely with researchers and building tooling to support research teams; or directly performed research with complex engineering challenges

Responsibilities

  • Build and maintain the specialized inference and training infrastructure that powers interpretability research - including instrumented forward/backward passes, activation extraction, and steering vector application
  • Resolve scaling and efficiency bottlenecks through profiling, optimization, and close collaboration with peer infrastructure teams
  • Design tools, abstractions, and platforms that enable researchers to rapidly experiment without hitting engineering barriers
  • Help bring interpretability research into production safety audits - with real deadlines and high reliability expectations
  • Work across the stack - from model internals and accelerator-level optimization to user-facing research tooling

Technologies

PythonRustGoJavaPyTorchCUDAJAXXLA

Compartilhar vaga

Descubra se seu currículo está pronto para esta vaga

Veja como nossa IA pode otimizar seu currículo e aumentar suas chances de conseguir esta posição.