Job Details

About the job

This role is being recruited by Reeval on behalf of one of our customers.

We work directly with candidates to understand their experience and match them to high-quality opportunities. If there's a strong fit, we introduce you to the company.

Next step: Talk to a recruiter from our team to get considered for this role.

Role description

You will work on the systems that make Respan intelligent: automated evaluations, prompt optimization, model routing, and AI-powered analysis of traces and logs.

This is deeply technical AI engineering — not just API calls.

We're looking for someone who understands LLM systems end-to-end and can build reliable, production-grade AI infrastructure used by real teams.

Responsibilities

• Design and build AI-powered systems (eval frameworks, prompt optimization)
• Develop LLM-as-judge pipelines for automated quality assessment
• Build model routing, caching, and fallback systems
• Experiment with new model capabilities and ship them into production
• Work closely with users to understand AI workflow pain points

Minimum qualifications

• Strong software engineering skills (Python, TypeScript)
• Experience building LLM-powered systems in production
• Deep understanding of prompt engineering and model behavior
• Willingness to work in-person in the Bay Area

Preferred qualifications

• Experience with fine-tuning, RAG, or agent frameworks
• Background in ML infrastructure or MLOps
• Familiarity with observability or developer tooling
• Open-source contributions in AI/ML

Application process

You'll first speak with a recruiter to discuss your background and goals.

If there's a strong match, we'll introduce you directly to the hiring team.

• You can find more details and get started through Reeval.