Systematically test prompt engineering to ensure accurate AI outputs for legal teams.
Translate legal expertise into product features and workflow enhancements.
Collaborate with Engineering on LLM calls; review outputs for quality.
Translate client requests into concrete prompts and eval criteria; iterate prompts.
Benchmark model performance for various legal tasks; design rigorous tests.
Dataset curation and labeling for testing; model edge-case coverage.

🎯 Requirements

3+ years of relevant legal experience; JD preferred.
Exceptional writing; interest in AI in law.
Familiarity with coding agents (gemini-cli, claude-code, codex-cli).
Experience with generative AI in legal work; evaluating outputs and metrics.
Curious, detail-oriented, pragmatic; bridges data science with product.

🎁 Benefits

Equity program
401(k) with company match
Health, dental, and vision
17 vacation days + 11 holidays
Modern Health membership
Flexible WFH Tue & Fri; monthly internet stipend

Apply on employer's website

This employer gathers applications via their own applicant tracking system.

You will be redirected to an external application form.

Share job

Meet JobCopilot: Your Personal AI Job Hunter

Automatically Apply to Engineering Jobs. Just set your preferences and Job Copilot will do the rest — finding, filtering, and applying while you focus on what matters.

Activate JobCopilot