AI / LLM Evaluation QA jobs in San Francisco, United States
A mid-level AI / LLM Evaluation QA in San Francisco earns a median of $130k a year ($130k gross). San Francisco has about 828,000 residents and is the 17th largest of the 62 United States cities we list. PassRidge lists 2 open AI / LLM Evaluation QA roles based here.
Open AI / LLM Evaluation QA roles in San Francisco
2 roles based in San Francisco, then the levels we place here. Placement pay starts at the higher of the city and national median.
AI Evaluation Infrastructure Engineer
Research Engineer, Model Evaluation and Improvement
Junior AI Quality Analyst
AI Quality Analyst
Senior AI Quality Analyst
Lead AI Quality Analyst
"Talent pipeline" cards are the levels we place, not an employer's vacancy. Real postings are labelled "Market listing". How pay is set.
AI / LLM Evaluation QA pay by level in San Francisco
Gross annual pay in USD. San Francisco is 1.22× the United States median (+22%), which is $100k at mid-level.
| Level | p10 | Median | p90 | Range | Median (USD) |
|---|---|---|---|---|---|
| Junior | $71k | $87k | $110k | $87k | |
| Mid-level | $100k | $130k | $150k | $130k | |
| Senior | $150k | $180k | $220k | $180k | |
| Lead | $190k | $240k | $290k | $240k |
Estimates from posted pay ranges, base pay only. Full AI / LLM Evaluation QA salary page for San Francisco.
What a AI / LLM Evaluation QA does in San Francisco
Evaluates model outputs, writes rubrics and builds regression sets for AI features.
- Write evaluation rubrics and golden datasets
- Rate and compare model outputs at scale
- Red-team prompts for safety and policy gaps
- Build regression suites for prompt and model changes
- Report quality metrics to product teams
Skills and stack employers ask for
Tools named most often
Time zone
San Francisco is on America/Los Angeles. A 09:00-17:00 day shares 5 h with US East, 0 h with London and 0 h with Central Europe.
AI / LLM Evaluation QA jobs in other United States cities
Other QA roles in San Francisco
QA jobs, time zone and hiring facts for San Francisco · AI / LLM Evaluation QA role guide · Hire a AI / LLM Evaluation QA
AI / LLM Evaluation QA jobs in San Francisco: FAQ
How much does a AI / LLM Evaluation QA earn in San Francisco?
A mid-level AI / LLM Evaluation QA in San Francisco earns a median of $130k a year ($130k), with a p10 to p90 range of $100k to $150k. Junior pay starts near $87k, senior pay is $180k and leads reach $240k.
Are there AI / LLM Evaluation QA jobs in San Francisco?
Yes: 2 open AI / LLM Evaluation QA roles are based in San Francisco right now, 0 of them remote, and 32 in United States. Tell us your city and we alert you when a local role opens.
How does San Francisco pay compare with the rest of United States?
San Francisco ranks 1st of 62 United States cities we track for AI / LLM Evaluation QA pay, at 1.22x the national median (+22%). The national mid-level median is $100k, so San Francisco is above it. Against the US it is 30% above the US median of $100k.
What skills do AI / LLM Evaluation QA jobs in San Francisco ask for?
Evaluates model outputs, writes rubrics and builds regression sets for AI features. Typical requirements: Prompting, Evaluation design, Python, Domain expertise, Annotation tools. The tools named most often are Python, Jira, Postman.
Can a AI / LLM Evaluation QA work with US or European teams from San Francisco?
San Francisco is on America/Los Angeles. A 09:00-17:00 day shares about 5 h with US East, 0 h with London and 0 h with Central Europe. 85% of AI / LLM Evaluation QA roles are remote-friendly.
How do I get a AI / LLM Evaluation QA job in San Francisco with PassRidge?
Tell us your level and stack in the form on this page. A recruiter sends matching roles with the pay shown upfront; it is free for candidates and nothing goes to an employer without your written OK. Our placement range for San Francisco starts at the higher of the city and national median.