> Markdown version of [/jobs/ext/2691967-ai-systems-architect](https://www.wearedevelopers.com/jobs/ext/2691967-ai-systems-architect). Every page supports `.md` or `Accept: text/markdown`. Links point to the HTML versions so they work for humans too. Agent guide: [/agents.md](https://www.wearedevelopers.com/agents.md). --- # AI Systems Architect - **Company:** Jerry's, Incorporated - **Location:** San Francisco, CA, United States (Remote available) - **Experience:** Expert - **Contract:** Permanent contract - **Skills:** Artificial Intelligence, Amazon Web Services, Regression Analysis, Software Engineering, TypeScript, ReactJS, Large Language Models, Prompt Engineering, Low Latency, Graphql, NestJS - **Published:** September 3, 2026 - **Apply:** https://www.dice.com/job-detail/5fa9c79c-7b91-4335-9f61-c1443dcca9bb ## About the Role * 5+ years in software engineering, ideally at an early-stage startup where you owned outcomes end-to-end. * You are a builder. You don't need someone else to write the spec. * Real, hands-on depth with AI: you've built with a new model within days of its release, and you can explain why one architecture or approach beats another - not just point at a demo. * Experience putting LLM-based systems into production, including the unglamorous parts: evals, regressions, latency, cost, and failure-handling. Our tech stack: TypeScript (Nest.js, React), GraphQL, AWS (ECS/EKS, Lambda), LLM models (OpenAI, Anthropic Claude, Google Gemini) ## Description Jerry.ai is a profitable, Series C, YC-backed tech startup with 5M+ customers and $240M in funding. We're building the first AI-powered advisor to manage all your physical assets. We started with car insurance in 2019, now we're expanding into new verticals (e.g. home, motorcycle, RV, boat) and accelerating our growth. The opportunity is massive - car insurance alone is a $300B market in the U.S. We spent the last few years building our supply (we work with 100+ insurance carriers) and our technical infrastructure (60% of policies today are sold automatically without human intervention, 90% of inbound customer inquiries are resolved via AI and automation). The next chapter is about accelerating our growth - going from 5M to 50M customers by 2030. The technical challenge: Our insurance marketplace is our core product today, and our ability to automate the end-to-end shopping experience is our core differentiator. The AI & Automation team owns the most critical part of that - how we automate the entire insurance quoting experience for our customers and orchestrate complex, multi-step transactions with external insurance provider systems to finalize policy purchases. Before off-the-shelf AI agents existed, we built our own proprietary infrastructure to scale automated insurance purchases and customer support. Today, 60% of insurance policies are sold automatically without human intervention, and 78% of inbound customer inquiries are resolved via AI and automation, with 83% reporting a positive experience. Our current system is working but our use cases are rapidly growing as our business expands beyond car insurance and available AI models are also evolving. We need someone to lead the charge in building our "next generation" AI system, including building new automations for things like document validation (drivers' licenses, proof of insurance, etc), voicebot expansion into stateful, phone-based interactions, and enable our bots to have direct external system navigation to resolve complex issues more quickly and accurately than human agents. What you'll own: * Set the technical bar for our chatbot systems - shape what the prompt engineering team builds next and keep the architecture sound as it scales. * Build new automations across areas like record disputes, email/callout reduction, document validation (ex. licenses, proof of insurance). * Evaluate emerging AI technology (voicebot, computer use agents, and beyond), make the call on what we invest in next, build and ship to production. * Partner with OpenAI to evaluate and deploy next-generation voice models and workflow automation. ## Related Videos - [You are not an AI developer](https://www.wearedevelopers.com/videos/1148-you-are-not-an-ai-developer) - [Nest.js - TypeScript in the backend can also be clean](https://www.wearedevelopers.com/videos/1033-nest-js-typescript-in-the-backend-can-also-be-clean) - [Watch Tests Go Brrrr! : Getting Started with Cypress in ReactJS](https://www.wearedevelopers.com/videos/282-watch-tests-go-brrrr-getting-started-with-cypress-in-reactjs) - [Putting the Graph In GraphQL With The Neo4j GraphQL Library](https://www.wearedevelopers.com/videos/257-putting-the-graph-in-graphql-with-the-neo4j-graphql-library) - [Bringing the power of AI to your application.](https://www.wearedevelopers.com/videos/1010-bringing-the-power-of-ai-to-your-application) - [Streaming AI Responses in Real-Time with SSE in Next.js & NestJS](https://www.wearedevelopers.com/videos/1630-streaming-ai-responses-in-real-time-with-sse-in-next-js-nestjs) ## Related Articles - [Graph and AI Trends 2026: Why Is AI Running but Not Yet Delivering?](https://www.wearedevelopers.com/magazine/680-graph-and-ai-trends-2026-why-is-ai-running-but-not-yet-delivering) - [Navigating the AI Shift](https://www.wearedevelopers.com/magazine/629-navigating-the-ai-shift) - [Never delegate the understanding](https://www.wearedevelopers.com/magazine/749-never-delegate-the-understanding) - [Dev Digest 137 - AI'm not sure about this](https://www.wearedevelopers.com/magazine/485-dev-digest-137-ai-m-not-sure-about-this) - [What is Software Engineering in the Age of AI?](https://www.wearedevelopers.com/magazine/640-what-is-software-engineering-in-the-age-of-ai) - [Dev Digest 120 - Apple and peers](https://www.wearedevelopers.com/magazine/455-dev-digest-120-apple-and-peers)