Prompt Engineer
Summary
Design and refine LLM workflows, evaluate model quality, and build evaluation frameworks to reduce hallucinations and improve AI agent performance.
- Build LLM as judge evaluation frameworks
- Collaborate with product marketing CX and R and D teams
- Design AI agents and LLM workflows
- Evaluate model quality at scale
- Implement fixes for hallucinations and regressions
- Monitor live systems and triage issues
- Prototype and iterate LLM workflows
- Write functions APIs and integrations
Perks/Benefits:
- Career advancement path
- Coffee
- Learning and growth opportunities
- Office treats