Build evals & harnesses that capture real‑world quality
Operationalize adoption: run trainings, write crisp runbooks, and hand off durable playbooks
Surface field patterns and translate them into platform components
Requirements
5–10+ years building and shipping software to production
Comfortable across APIs, data pipelines, backend services, and light UI glue
Hands-on with Python/TypeScript (or similar), modern cloud services, and telemetry/observability
Experience with LLM-enabled systems (RAG, tool use/agents, evals, guardrails) and data integration in messy enterprise environments
Strength in requirements discovery with non-technical stakeholders
Security-first mindset (RBAC, least privilege, data residency, auditability)
Domain familiarity with acquisition/CLM/procurement/RFPs is a strong plus (FAR/DFARS knowledge, public-sector experience, or exposure to regulated industries)
Clearance eligibility is a plus.
Tech Stack
Cloud
Python
TypeScript
Benefits
High Ownership role
Hands-on work across the stack
Regular on-site collaboration at customer locations