Research Engineer, Interpretability

Details

Anthropic’s mission is to create reliable, interpretable, and steerable AI systems. The Interpretability team focuses on mechanistic interpretability — discovering how neural network parameters map to meaningful algorithms — and builds tools and infrastructure to reverse-engineer how trained models work. Team work spans empirical research, tooling, large-scale data pipelines, and collaborations across Anthropic to improve model safety.

Responsibilities

• 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 a rapid pace of research experimentation
• Develop and improve tools and infrastructure to support other teams in using Interpretability’s work to improve model safety

Requirements

• 5–10+ years of experience building software
• Highly proficient in at least one programming language (examples listed: Python, Rust, Go, Java) and productive with Python
• Some experience contributing to empirical AI research projects
• Strong ability to prioritize and direct effort toward the most impactful work; comfortable operating with ambiguity and questioning assumptions
• Prefer collaborative, fast-moving projects
• Interest in learning machine learning research and collaborating closely with researchers
• Care about societal impacts and ethics of work
• Education: at least a Bachelor’s degree in a related field or equivalent experience

Strong candidates may also have experience with

• Designing a codebase so others can quickly run experiments, launch them, and analyze results without hitting bugs
• Optimizing performance of large-scale distributed systems
• Collaborating closely with researchers
• Language modeling with transformers
• GPUs or PyTorch

Representative projects / examples of work

• Building Garcon: a tool that allows researchers to easily access LLM internals from a Jupyter notebook
• Setting up and optimizing a pipeline to collect petabytes of transformer activations and shuffle them
• Profiling and optimizing ML training, including parallelizing to many GPUs
• Making launching ML experiments and analyzing results fast and easy
• Creating interactive visualizations of attention between tokens in a language model

Location & Office Policy

• This role is based in the San Francisco office; exceptional candidates may be considered for remote work on a case-by-case basis.
• Currently, staff are expected to be in one of Anthropic’s offices at least 25% of the time. Some roles may require more in-office time.

Compensation

• Annual base salary range: $315,000 - $560,000 USD
• Total compensation for full-time employees includes equity, benefits, and may include incentive compensation

Logistics

• Visa sponsorship: Anthropic does sponsor visas where feasible and retains immigration counsel to assist where possible
• Application materials: resume/CV or LinkedIn profile required; optional cover letter and links (GitHub, publications)

Why Anthropic / Culture

• Team values large-scale, high-impact empirical AI research and collaborative work across disciplines
• Emphasis on communication, safety, and societal/ethical implications of AI

How to apply

• Submit application via Anthropic’s careers page. Anthropic encourages applicants from diverse backgrounds and those who may not meet every listed qualification to apply.