A
Prompt Engineer
Anton Volkov
Full-time · Mid-level · Chicago
About the role
Have you ever looked at an LLM output and known immediately that the prompt was wrong — not the model, not the data, but the prompt? That's the instinct we're looking for. We are a legal tech company building AI-assisted contract review tools. Our prompts work. They just don't work consistently. We need someone systematic: someone who treats prompting like engineering, not like guess-and-check. You'll own the prompt layer for three of our core product features, with room to expand.
Responsibilities
- Own and improve prompts for contract summarisation, clause extraction, and risk flagging
- Build a prompt versioning system with performance benchmarks
- Run A/B tests on prompt variations and measure accuracy changes
- Work with lawyers on the team to validate output quality
- Document failure modes and keep a known-issues registry
Requirements
- 2+ years prompt engineering experience with real shipped products
- Able to build and run prompt regression test suites
- Familiarity with structured output techniques (JSON mode, function calling)
- Strong written communication — you document everything
- Plus: experience with legal or financial document use cases
Benefits
- Full remote
- $85,000 – $110,000 salary
- Conference budget
- High-quality domain work — not generic chatbot prompts
- Small team, high ownership
Job Type
Full-time
Level
Mid-level
Language
English
Salary Range
$85,000 – $110,000
AI Expertise
NLP & Prompt Engineering
Ready to apply for this role?
Create a free talent account in under 2 minutes.
- Apply to verified AI companies
- Get AI-matched job recommendations
- Message hiring managers directly
- Build your public AI talent profile