Job brief: Research Engineer, Interpretability

Anthropic · San Francisco, CA · facts as of 2026-11-06. Anyone can open this page; no account needed.

Is it still open? · Checked by JoRoute

Still listed. JoRoute saw it on Anthropic's own job board 3 hours ago; the employer first posted it on 2025-11-07.

What JoRoute checked · Checked by JoRoute

  • Listed on Anthropic's own job board. JoRoute does not take listings from job ads or recruiters.
  • First seen by JoRoute 2026-11-04 (2 days ago); last confirmed on the board 2026-11-06.
  • The apply link opens job-boards.greenhouse.io, the address Anthropic's board gives for this job.
  • No other listing with this title and place on this board in the last 90 days.
  • No layoff notices (WARN) under this name in the state files JoRoute reads.

What the listing says · Employer's own words, not checked

  • Pay: $315,000 to $560,000 a year
  • Job type: Not stated
  • Where: San Francisco, CA
  • Posted: 2025-11-07 · over 60 days ago

What the job asks · Employer's own words, not checked

Level: Senior. The posting asks for 10+ years of experience.

Must have

  • Have 5-10+ years of experience building software
  • Are curious about interpretability research and its role in AI safety (though no research experience is required!)
  • 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

Conditions

  • 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.

Main duties

  • Build and maintain the specialized inference and training infrastructure that powers interpretability research - including instrumented forward/backward pass…
  • 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

Lines copied from the posting, not rewritten. "Preferred" or "nice to have" items are not listed as must-haves.

How it compares · Compared by JoRoute from listings

  • Typical listed pay for engineer jobs in San Francisco, CA: $193k a year (679 listings, 42 employers). This listing is 127% higher.
  • Across Anthropic's 541 open listings, 54% of those with a posting date were first posted more than 60 days ago. How Anthropic hires

What nobody outside the employer knows · Not known

  • Whether the role is already filled or on hold: employers often leave listings up.
  • How many people applied, and who reads the applications.
  • Where in the published range an offer would land.

Ask before you apply

  1. Is this role still open, and when do you hope to fill it?
  2. What are the interview steps, and when should I expect to hear back?

Share this brief

Send it to someone whose opinion you trust. They can open it without an account, and nothing about you is in the link.

Email itText it

To keep a copy, use your browser's Print or Share button.

Next steps

Apply on the employer's page Full listingDoes my CV fit?Practise the interviewShould I apply?

Got a message about this job asking for money or documents? Check the message first.

Keep looking

A summary of facts and listings, not a verdict that this job or employer is safe. JoRoute is not affiliated with Anthropic. How JoRoute checks listings · Original posting