Research Engineer (Interpretability)

About the role

Join Anthropic's Interpretability team as a Research Engineer. You'll work on mechanistic interpretability, reverse-engineering how trained models work to ensure their safety. Your responsibilities will include implementing and analyzing research experiments, optimizing research workflows, and developing tools to support rapid experimentation. You'll collaborate with various teams across Anthropic and contribute to projects that enhance model safety. Key missions: Implement and analyze research experiments, both quickly in toy scenarios and at scale in large models.. Set up and optimize research workflows to run efficiently and reliably at large scale.. Build tools and abstractions to support rapid pace of research experimentation. Profile: - When you see what modern language models are capable of, do you wonder, "How do these things work? How can we trust them?" - Are highly proficient in at least one programming language (e.g., Python, Rust, Go, Java) and productive with python - Have a strong ability to prioritize and direct effort toward the most impactful work and are comfortable operating with ambiguity and questioning assumptions - Prefer fast-moving collaborative projects to extensive solo efforts - Care about the societal impacts and ethics of your work - Have 5-10+ years of experience building software - Have some experience contributing to empirical AI research projects - Want to learn more about machine learning research and its applications and collaborate closely with researchers - Designing a code base so that anyone can quickly code experiments, launch them, and analyze their results without hitting bugs - Collaborating closely with researchers - GPUs or Pytorch - Education requirements: We require at least a Bachelor's degree in a related field or equivalent experience - We encourage you to apply even if you do not believe you meet every single qualification. Not all strong candidates will meet every single qualification as listed - Research shows that people who identify as being from underrepresented groups are more prone to experiencing imposter syndrome and doubting the strength of their candidacy, so we urge you not to exclude yourself prematurely and to submit an application if you're interested in this work - Optimizing the performance of large-scale distributed systems - Language modeling with transformers