AI EvalsJobs
Hiring?
All roles / AI Evaluation & Benchmark Jobs

AI Evaluation & Benchmark Jobs

393 open roles at Anthropic, OpenAI, Google DeepMind and 109 other companies, straight from their own career pages.

What changed on this board this weekWhat changed since last Thursday: new roles, roles that closed, and pay moves.

Search all jobs → · Results below are paginated for fast, complete crawling.

Live market snapshot

What this market looks like today

393open roles
112employers
12%remote-listed
52%publish pay

Largest hiring clusters. Waymo (25), Wayve (22), Scale AI (21), Apple (20), Anthropic (16). Common listed locations. san francisco (68), san francisco, ca (31), mountain view, ca, usa (19), london (17), new york, ny (12). Median advertised top of band. $310,000 among roles with comparable published pay.

Method. Recomputed from the live jobs on this exact page after the daily employer-source crawl. Counts describe advertised openings, not hires or headcount. “Remote” means the employer lists remote work; it does not imply worldwide eligibility. Pay disclosure is the share of these postings with a machine-readable advertised band. Historical velocity will be added only after enough daily observations exist to make the comparison meaningful.

393 roles

Berkeley Office · Remote (US) +2Remote listed$150k – $250k

Evals & BenchmarksFull time10mo ago

Palo Alto, California, United States · San Francisco, California, United States +1$250k – $350k on-target+ equity

Evals & Benchmarks10mo ago

*HQ - San Francisco, CA$220k – $350k+ equity

Evals & BenchmarksFull time11mo ago

San Francisco, California$180k – $350k+ equity

Evals & BenchmarksFull time11mo ago

San Francisco$130k – $500k+ equity

Evals & BenchmarksFull time13mo ago

Palo Alto, CA

Evals & BenchmarksFull time14mo ago

Berkeley Office · Remote (US) +2Remote listed$120k – $190k

Evals & BenchmarksFull time18mo ago

Oakland, CA ( · remote within US timezones)Remote listed$220k+ equity

Evals & BenchmarksFull time69mo ago

What changed this week

This board rebuilds every morning, so the version you are reading is already different from last week's. Thursdays we send the difference: roles that opened, roles that closed, and the companies that moved their published pay. Compare the changes with the full listings on the board.

Get Thursday's changes

Location
Compensation
Track

The full description, what the posting asks for, and the employer's own application link are on the listing page.

Privacy · Terms