Build retrieval-grounded assistants and automation that hold up under enterprise evaluation and governance.
Responsibilities
- Design and ship retrieval-grounded AI features on client data
- Build evaluation harnesses that make quality measurable
- Integrate guardrails, audit trails and human review gates
- Work directly with client engineering teams through delivery
Requirements
- Production experience with LLM applications, not just prototypes
- Strong Python and API design fundamentals
- A rigorous approach to measuring model output quality
- Comfort working in regulated or security-sensitive environments
Benefits
- Comprehensive medical, dental and vision cover
- 401(k) with employer contribution
- Conference and research budget
- Hybrid working from our Dallas office