AI Engineer

Vouch is the insurance broker that powers ambition. We’re a tech-enabled insurance advisory and brokerage purpose-built for growing companies in technology, life sciences, and professional services. Our clients are ambitious leaders building complex businesses, and we help them manage risk with tailored advice, smart coverage, and responsive service. Backed by over $200M from world-class investors, Vouch combines deep industry expertise with AI-powered tools to deliver a better insurance experience. Our digital workflows reduce friction, speed up decisions, and give our clients the confidence to move faster.

About the role

Vouch is building AI software for judgment-heavy insurance work: a system that learns from experts and gets measurably better week over week. We are early — a small team, real experts, real production usage, real customers, and a lot of unanswered technical questions. This is genuinely interesting work in a regulated domain where being wrong has consequences. The hard problems live in making an LLM system durable, auditable, and measurably improving.

You would join early in the system's life, in a rapidly evolving codebase that already carries more test code than source code. That ratio is intentional; it reflects our style. How we work:

• Reasoning is written down and public — design docs land as pull requests, root-cause writeups happen in the channel, and demos are async videos every Friday morning.
• We ship to staging many times a day and to production behind consent-based pushes.
• Standups are short and bot-recapped; real arguments happen in threads and design-doc reviews.

Responsibilities

• Ship agentic workflows end to end. Design tool contracts, capability boundaries, and approval gates for an agent doing real insurance work under human judgment — then carry your change through review, deploy, and production ownership.
• Build on a durable-execution backbone. Our workflows run with pinned worker versioning and a replay-compatibility gate in CI; a crashed worker must resume mid-workflow without losing state. You'll extend that substrate and understand it deeply.
• Make model behavior measurable. Deterministic corpus tests are the merge gate; eval suites are the diagnostics; characterization corpora pin behavior before refactors. You'll maintain and grow that machinery, along with LLM tracing and token/cost observability.
• Treat prompts and tool definitions as engineered artifacts — versioned, cache-stable, snapshot-tested, and reviewed like code, because they are code.
• Run the event and data substrate. Event bus with schema-governed domain events, object storage, OLTP/OLAP databases, and the two-way plumbing between an agent and the systems of record it must respect.
• Work with AI, on AI. Use frontier coding agents as daily instruments, and build the system that makes an AI coworker trustworthy.
• Review with teeth. Our review culture prizes finding the silent failure path — the empty string that detonates three stages later — before production does.

Requirements

• You are AI-native and inventive. Frontier models are instruments you play daily — in how you build (coding agents, multi-model workflows) and in what you build (planners, classifiers, tool-calling systems). You prototype fast, generalize what survives contact with reality, and delete what doesn't.
• You are steady in delivery and reasoning. You ship in small, traceable increments, week after week; teammates can find the ticket from your branch name and the reasoning in your design doc.
• You write your thinking down — design docs before lynchpin systems, and review comments that catch what tests miss.
• Production is yours. You fix the OOM at the right layer and treat a correctness rework as finishing the job, not a "fast follow".
• You simplify your own work: deleting your days-old code because a simpler approach developed is a win, not a loss.
• Table-stakes production service fundamentals: API design, data contracts, authorization boundaries, observability.
• Hands-on experience with LLM agent systems — tool-calling patterns, MCP, the Anthropic SDK, or equivalents — running in front of real users.
• Fluency in a strictly-typed codebase.
• You put safety properties in code, not in prompts — and you can say why.
• Clear written communication about tradeoffs; here, decisions live in documents and threads.
• Prior experience in and passion for early-stage startups and/or high-growth environments.

Nice-to-haves

• Experience with durable-execution engines in production.
• Event-driven systems with schema governance — event bus patterns, pub/sub, schema registry, Avro/Protobuf.
• Eval frameworks and LLM observability.
• Building and consuming MCP servers.
• Data lake or warehouse-adjacent data engineering.
• A regulated domain — insurance, fintech, healthcare — where correctness is contractual.
• Frontend experience; it's where our users live.

Work environment

Vouch has employees located across the U.S., with offices in San Francisco, Chicago, and New York City. While this role has hybrid work flexibility, we require team members to be in the office at least three days per week (Tuesday, Wednesday, and Thursday) to foster close collaboration and team building.

Benefits

• Competitive compensation and equity packages
• Health, dental, and vision insurance
• Parental leave
• Flexible vacation time
• Wellness allowance
• Technology allowance
• Company-sponsored personal and professional development
• L&D: Partnerships with Ethena and monthly Lunch & Learns
• Wellbeing: Access to many wellbeing perks, including Peloton, Fetch, OneMedical, Headspace care+, etc.
• Caregiver Support: Company seed into the dependent care FSA and company-sponsored Care.com membership
• Regular performance reviews: Goal setting, check-ins, development discussions, and promotion opportunities

Pay

The pay range for this role is $180,000 - $220,000 USD per year (Chicago, IL - Hybrid).