AI / LLM Evaluation QA jobs: remote, hybrid and Flex
A AI / LLM Evaluation QA evaluates model outputs, writes rubrics and builds regression sets for AI features. In the US the median is $104k a year for a mid-level hire, $71k at junior and $148k at senior. We have 102 open AI / LLM Evaluation QA roles in 27 countries, 51 of them remote.
Live AI / LLM Evaluation QA roles
QA Specialist - AI Governance Platform
Research Scientist, AI Evaluation Science
AI Native, QA Engineer
Data Scientist, AI/ML Model Quality
AI-Native Software Engineer, QA Automation
Graduate Software Engineer, AI/ ML Test Systems 2027
What a AI / LLM Evaluation QA earns
Median gross annual pay by level, in local currency. Estimates from public statistics and our listings.
| Country | Junior | Mid | Senior | Lead |
|---|---|---|---|---|
| United States | $71k | $100k | $150k | $190k |
| United Kingdom | £33k | £48k | £69k | £90k |
| Germany | €39k | €58k | €82k | €110k |
| Netherlands | €39k | €58k | €82k | €110k |
| Poland | PLN 110k | PLN 170k | PLN 240k | PLN 310k |
| Portugal | €22k | €32k | €46k | €59k |
| India | ₹1.1M | ₹1.6M | ₹2.3M | ₹3M |
| Brazil | R$170k | R$250k | R$360k | R$470k |
What a AI / LLM Evaluation QA does
- 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
Where this role goes
Junior
Learns the product and the toolchain. Executes cases, reports clean bugs.
US median $71k
Mid
Owns a feature area end to end. Designs tests and mentors juniors.
US median $104k
Senior
Sets approach for a team. Reviews, unblocks and raises the quality bar.
US median $148k
Lead
Owns strategy, hiring and quality reporting across teams.
US median $193k
Common moves from AI / LLM Evaluation QA: Manual QA Tester, Localization QA Tester, Data / ETL QA Engineer.
AI / LLM Evaluation QA work in 3–4 hour windows
Take project tasks next to your main job. Rates start at $15/hour and are shown before you apply.
AI / LLM Evaluation QA FAQ
How much does a AI / LLM Evaluation QA earn?
In the US the median gross salary is $104k for mid-level, ranging from $71k (junior) to $193k (lead). In the UK a mid-level AI / LLM Evaluation QA typically earns £48k and in Germany €58k.
What skills does a AI / LLM Evaluation QA need?
Prompting, Evaluation design, Python, Domain expertise, Annotation tools. Employers also look for evidence: a test strategy you wrote, a framework you built, or defects you found.
Can I work remotely as a AI / LLM Evaluation QA?
Yes. About 85% of AI / LLM Evaluation QA roles in our network are remote or remote-friendly. Time-zone overlap with the client is usually the deciding factor.
Which tools should a AI / LLM Evaluation QA know?
The most common in our listings: Python, Jira, Postman.
Can I do AI / LLM Evaluation QA work part-time through Flex?
Yes. PassRidge Flex offers project tasks of 3-4 hours a day, paid hourly or per project. Check your main employer's contract for moonlighting rules first.