Software Architect, AI & Automation

About the role

Jerry.ai is a profitable, Series C, YC‑backed tech startup with over 5 M customers and $240 M in funding. We are building the first AI‑powered advisor to manage all your physical assets — starting with car insurance in 2019 and now expanding into home, motorcycle, RV, boat and beyond. The U.S. car insurance market alone is $300 B, and we have already built a supply network of 100+ insurance carriers and a technical infrastructure where 60% of policies are sold automatically and 78% of inbound customer inquiries are resolved via AI and automation. Our next chapter is to accelerate growth from 5 M to 50 M customers by 2030 by leading the development of our “next generation” AI system.

The AI & Automation team owns the end‑to‑end insurance quoting experience, orchestrating complex, multi‑step transactions with external carrier systems. We need a technical leader to build new automations for document validation, expand voicebot capabilities into stateful phone interactions, and enable bots to navigate external systems directly to resolve issues faster and more accurately than human agents.

Responsibilities

• Agentic/conversational front end — shape the chatbot, voicebot, and computer‑use agents; guide the prompt engineering team’s next builds and maintain a sound, scalable architecture.
• Backend workflow automation — create new automations for document validation (e.g., drivers’ licenses, proof of insurance), record disputes, and transaction orchestration with external carrier systems.
• Evaluate emerging AI technologies (voicebot, computer‑use agents, and beyond), decide where to invest, and build and ship solutions to production.
• Partner with OpenAI to evaluate and deploy next‑generation voice models and workflow automation.

Requirements

• 5+ years of software engineering experience, preferably at an early‑stage startup where you owned outcomes end‑to‑end.
• You are a builder at heart — you don’t need someone else to write the spec.
• You have tinkered with new models shortly after release and can articulate why one architecture or approach is superior to another.
• Proven experience putting LLM‑based systems into production, including handling evals, regressions, latency, cost, and failure‑handling.
• Eligible to work full‑time from one of the following locations: AZ, CA, CO, FL, GA, IL, MA, NC, NJ, NV, NY, OR, TN, TX, UT, VA, or Ontario, Canada (full‑time salaried); or AZ, FL, GA, NV, NY, NC, TN, TX, UT, or VA (full‑time hourly).

Skills

• TypeScript (Nest.js, React)
• GraphQL
• AWS (ECS/EKS, Lambda)
• LLM providers: OpenAI, Anthropic Claude, Google Gemini

Benefits

• Health, dental, and vision coverage
• Paid time off and paid parental leave
• 401(K) plan with employer matching
• Wellness benefits
• Equity opportunities as part of total rewards
• Remote‑first work environment with optional in‑person/hybrid options at offices in Palo Alto, New York City, Chicago, and Toronto