- Help build GenAI solutions from prototype to production.
- Lead prompt engineering: system/tool prompts, function calling, prompt versioning with offline/online evals.
- Implement evaluation & observability with ground source of truth establishment, confusion metrics, and LLM-as-judge with human review
- Use proficiency in Python to streamlining evaluation tasks
- Leverage understanding of retrieval strategies, prompt patterns, model context management, and hallucination mitigation.
- Security/privacy mindset (PII handling, RBAC), and practical cost/performance tuning
Job Type: Contract
Pay: $60.00 - $65.00 per hour
Expected hours: 40 per week
Work Location: In person