About the role
SureBright is hiring an AI Engineer to build the agentic layer of its warranty platform - AI systems that reason, take actions, and complete real workflows across pricing/underwriting, policy issuance, claims intake, and fulfillment. This is a high-ownership, founder-speed role covering the full stack of an insurance/warranty business.
What you'll do
Design and ship production-grade AI agents that run real business processes, not demos
Build agentic architectures: orchestration, tool calling, state machines, audit trails, human-in-the-loop
Own the RAG platform end-to-end: ingestion, retrieval, reranking, grounding, hallucination mitigation
Build evaluation and monitoring systems: offline eval sets, regression tests, drift detection
Build core ML systems for warranty/claims: document understanding, extraction, fraud signals
What we're looking for
1++ years of relevant experience
1+ years building and shipping ML/LLM systems in production (or equivalent founder-level experience)
Proven experience building agentic products: multi-step workflows, tool use, orchestration, reliability engineering
Deep hands-on expertise in RAG/retrieval systems, LLM evals, and prompting/structured outputs
Model training/fine-tuning fundamentals and tradeoffs (when to tune vs prompt vs retrieve)
Strong software engineering: clean APIs, testing, observability, secure-by-default design
Nice to have
Experience building systems with compliance/audit requirements (fintech/insurance/health/enterprise)Experience with document AI at scale (PDFs, images, messy inputs)Startup or ex-founder background, especially shipping 0-to-1 products fast