Research Engineer, Interpretability
About the role
The Interpretability team at Anthropic is working to reverse-engineer how trained models work because we believe that a mechanistic understanding is the most robust way to make advanced systems safe. Think of us as doing "neuroscience" of neural networks using "microscopes" we build - or reverse-engineering neural networks like binary programs.
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
Requirements
- 5-10+ years of experience building software
- Highest proficiency in at least one programming language (e.g., Python, Rust, Go, Java)
- 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
- A strong ability to prioritize the most impactful work and are comfortable operating with ambiguity and questioning assumptions
- Careful about the societal impacts and ethics of your work
- Curious about interpretability research and its role in AI safety (though no research experience is required!)
Qualifications
- Prefer fast-moving collaborative projects to extensive solo efforts
- Strong Candidates May Also Have Experience With 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
Skills
- Representative Projects
- Building Garcon, a tool that allows researchers to easily instrument LLMs to extract internal activations
- Designing and optimizing a pipeline to efficiently collect petabytes of transformer activations and shuffle them
- Profiling and optimizing ML training jobs, including multi-GPU parallelism and memory optimization
- Building a steered inference system that applies targeted interventions to model internals at scale (conceptually similar to Golden Gate Claude but for safety research)
Benefits
- Annual compensation range for this role is listed below. For sales roles, the range provided is the role’s On Target Earnings ("OTE") range, meaning that the range includes both the sales commissions/sales bonuses target and annual base salary for the role.
- Annual Salary $315,000—$560,000 USD
Pay
- $315,000—$560,000 USD
Schedule
- Currently, we expect all staff to be in one of our offices at least 25% of the time. However, some roles may require more time in our offices.
Location Policy
This role is based in the San Francisco office; however, we are open to considering exceptional candidates for remote work on a case-by-case basis.
Logistics
- Minimum education: Bachelor’s degree or an equivalent combination of education, training, and/or experience
- Required field of study: A field relevant to the role as demonstrated through coursework, training, or professional experience
- Minimum years of experience: Years of experience required will correlate with the internal job level requirements for the position
Role Specific Location Policy
This role is based in the San Francisco office; however, we are open to considering exceptional candidates for remote work on a case-by-case basis.
Visa Sponsorship
We do sponsor visas! However, we aren't able to successfully sponsor visas for every role and every candidate. But if we make you an offer, we will make every reasonable effort to get you a visa, and we retain an immigration lawyer to help with this. 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.
Guidance on Candidates' AI Usage
Learn about our policy for using AI in our application process.