AI Engineer

About the Role

This is a high-ownership, do-whatever-it-takes role for an individual eager to operate at founder speed. You will gain a comprehensive understanding of the full stack of an insurance/warranty business and deliver work that directly impacts revenue, conversion, and retention.

What You'll Do

You will be instrumental in building the agentic layer of our core product. This involves developing AI systems capable of reasoning, taking actions, and reliably completing complex workflows across critical business areas such as pricing, underwriting, policy issuance, claims intake, adjudication, fulfillment (repair/replacement/reimbursement), and other operational facets.

Key Responsibilities

• Design and deploy production-grade AI agents that execute real business processes, not just demonstrations.
• Construct agentic architectures, encompassing orchestration, tool calling, state machines, memory management, permissions, audit trails, human-in-the-loop mechanisms, and fallback strategies.
• Take end-to-end ownership of our RAG (Retrieval-Augmented Generation) platform, including ingestion, chunking, embeddings, retrieval, reranking, citation/grounding, and hallucination mitigation.
• Develop robust evaluation and monitoring systems, including offline evaluation sets, regression tests, online metrics, drift detection, and red-teaming suites.
• Implement model optimization techniques such as prompt systems, structured outputs, fine-tuning where appropriate, latency/cost optimization, caching, and throughput tuning.
• Build core ML systems for warranty and claims processing, focusing on document understanding, extraction, classification, anomaly/fraud signal detection, decision support, and SLA routing.
• Collaborate closely with product and operations teams to translate real-world workflows into deterministic, testable, and compliant automation.

What You'll Build (Examples)

• Underwriting/Pricing Agents: Develop agents for real-time quote decisions, leveraging merchant, product, and context signals, with strict guardrails and auditability.
• Claims Copilot + Auto-Adjudication Engine: Create systems for claims intake triage, evidence requests, decision proposals with explanations, vendor routing, and reimbursement automation.
• OEM Warranty Parsing System: Build a system to convert complex manufacturer policies into machine-readable coverage logic.
• Internal Ops Copilots: Develop tooling to reduce manual effort and enhance consistency across customer support, compliance, and finance departments.

Requirements (Must Have)

(Hiring at different levels for the same role; required experience years and expected skill level will vary based on role level.)

• Minimum 1 year of experience building and shipping ML/LLM systems in production, or equivalent founder-level experience.
• Proven experience building agentic products or companies, demonstrating expertise in multi-step workflows, tool use, orchestration, and reliability engineering.
• Deep hands-on expertise in:
  • RAG and retrieval systems (including vector databases, reranking, and grounding strategies).
  • LLM evaluations (golden sets, automated judging, human evaluation, regression pipelines).
  • Prompting and structured outputs (schemas, function/tool calling, robustness).
  • Model training/fine-tuning fundamentals and understanding the trade-offs (when to tune vs. prompt vs. retrieve).
• Strong software engineering skills, including clean API design, testing, observability, performance tuning, and secure-by-default design principles.
• Comfortable taking ownership of ambiguous problems from start to finish and driving them to measurable outcomes.

Strong Preference (Nice to Have)

• Experience building systems with compliance and audit requirements (e.g., in fintech, insurance, health, or enterprise sectors).
• Experience with document AI at scale, handling diverse inputs (PDFs, images, messy text) and reliably extracting structured information.
• Experience designing human-in-the-loop workflows and escalation rules for high-stakes decision-making processes.
• Experience with infrastructure for LLMs, including model hosting, batching, streaming, caching, and prompt/version management.
• Startup or ex-founder background, particularly with a track record of shipping 0-to-1 products rapidly.

What Success Looks Like (First 90 Days)

• You will ship an agentic workflow that significantly reduces manual operations work and improves a measurable metric (e.g., cycle time, accuracy, cost per claim, attach rate, CSAT).
• You will implement an evaluation harness that effectively catches regressions before they reach production and provides a reliable quality score for each workflow.
• You will establish a scalable architectural pattern for agents, incorporating permissions, audit logs, observability, and fallbacks, that the team can readily replicate.

Tech Environment

We operate a cloud-native environment and maintain a rapid development pace. Expect to work with Python for ML/agents, TypeScript for product interfaces, Postgres for systems of record, and event-driven services. Our stack includes a modern LLM and retrieval system, supported by robust observability and CI/CD pipelines. Infrastructure is managed across AWS and Azure.

Why This Role is Special

• Opportunity to build an AI-native, category-defining company in a vast market.
• Direct exposure to founders and high leverage: your contributions will significantly influence the company's trajectory.
• Experience genuine breadth across growth, underwriting/claims operations, and product development within a single role.
• A career accelerant: strong performance will lead to rapid growth in scope and title.

How To Apply

• Please ensure your profile is up to date and includes a link to your LinkedIn profile.
• In your application message, briefly describe 3 key things you've built or delivered, along with their achieved results, using one simple sentence per example (total of 3 sentences).