Back to results
Technology & IT

Research Engineer, Interpretability - Anthropic - US

On-site · San Francisco, California Mid-level USD 315k–560k / yr Posted just now International
Apply on company site ↗
Not ready to apply yet?
Free ATS check

Check your CV before you apply

See your score the way hiring software reads it. If it needs work, build a stronger resume in the same place.

About the role

Anthropic is hiring a Research Engineer, Interpretability in San Francisco, the United States. Anthropic’s mission is to create reliable, interpretable, and steerable AI systems. We want AI to be safe and beneficial for our users and for society as a whole. Our team is a quickly growing group of committed researchers, engineers, policy experts, and business leaders working together to build beneficial AI systems.

Key responsibilities

  • Our research blog - covering advances including Monosemantic Features and Circuits
  • An Introduction to Interpretability from our research lead, Chris Olah
  • The Urgency of Interpretability from CEO Dario Amodei
  • Engineering Challenges Scaling Interpretability - directly relevant to this role
  • 60 Minutes segment - Around 8:07, see a demo of tooling our team built
  • New Yorker article - what it's like to work on one of AI's hardest open problems
  • Pretraining: Training dictionary learning models looks a lot like model pretraining - creating stable, performant training jobs for massively parameterized models across thousands of chips
  • Inference: Interp runs a customized inference stack. Day-to-day analysis requires services that allow editing a model's internal activations mid-forward-pass - for example, adding a "steering vector"
  • Performance: Like all LLM work, we push up against the limits of hardware and software. Rather than squeezing the last 0.1%, we are focused on finding bottlenecks, fixing them and moving ahead given rapidly evolving research and safety mission
  • Build and maintain the specialized inference and training infrastructure that powers interpretability research - including instrumented forward/backward passes, activation extraction, and steering vector application

Requirements

  • Have 5-10+ years of experience building software
  • Are highly proficient in at least one programming language (e.g., Python, Rust, Go, Java) and productive with Python
  • Are 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
  • Have a strong ability to prioritize the most impactful work and are comfortable operating with ambiguity and questioning assumptions
  • Prefer fast-moving collaborative projects to extensive solo efforts
  • Are 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
  • Are comfortable working closely with researchers, translating research needs into engineering solutions
  • Optimizing the performance of large-scale distributed systems

About Anthropic

Anthropic’s mission is to create reliable, interpretable, and steerable AI systems. We want AI to be safe and beneficial for our users and for society as a whole. Our team is a quickly growing group of committed researchers, engineers, policy experts, and business leaders working together to build beneficial AI systems.

Location and schedule

  • Based in San Francisco, the United States (onsite role)
  • 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
  • Location-based hybrid policy: 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

Salary and benefits

The posting states a base salary of USD 315,000 to 560,000 a year.

How to apply

Apply on the company's own site.

Anthropic
Listed via Employer Career Pages
View companies

Source: Employer Career Pages · The Briefed never charges candidates.

The Weekly Brief

New roles, in your inbox.

One email a week — the best hand-picked roles, salary insights and career reads. No spam, unsubscribe any time.