Lone Star Autonomy is hiring a Senior Senior LLM Engineer — tool use & workflows on the Applied research team (Hybrid · Austin, United States). This is a hands-on role in LLM & generative AI—not a generic “AI enthusiast” post.
You will own LLM features, retrieval, agents, and evaluation end to end: problem framing, offline evaluation, safe rollout, and iteration from production signals. Success is measured with clear metrics (quality, latency, cost, or business KPIs)—not slide decks alone.
Lone Star Autonomy delivers agentic assistants for professional services and internal ops teams across the US. We emphasise transparency, approvals, and traceability—not black-box autonomy.
Join our Austin office (hybrid) as a Senior LLM Engineer focused on tool use, workflow engines, and enterprise SSO.
What you will do
- Implement durable workflows with human-in-the-loop checkpoints, audit logs, and replay tooling.
- Integrate third-party APIs with robust auth (OAuth, SAML) and least-privilege patterns.
- Partner with design on progressive disclosure of agent plans to end users.
- Own evaluation loops for tool-selection accuracy and hallucination rates on critical actions.
- Participate in customer office hours for debugging complex agent traces.
What we look for
- 5+ years shipping Python services; 2+ years on LLM applications with tools.
- Experience with vector stores, structured outputs, and schema validation for tool args.
- Startup mindset: scope negotiation, fast iteration, and documentation despite speed.
- US work authorisation.
Nice to have
- LangGraph-style state machines or Temporal workflows in production.
- Background in ERP, legaltech, or document-heavy SaaS domains.