Software Architect, AI & Automation

Why you should join us:

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.

Note: You may see different job ads for this role at different job levels. We are only hiring one person. Our priority is finding the right person, we can be flexible with job title/leveling.
What you’ll own:

-

Own our AI agents and automation system, which has two components:

-
Agentic/conversational front end — chatbot, voicebot, computer-use agents; shape what the prompt engineering team builds next and keep the architecture sound as it scales.

-
Backend workflow automation — build new automations for things like document validation (ex. licenses, proof of insurance), record disputes, transaction orchestration with external carrier systems

-
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.

Who you are:

-
5+ years in software engineering, ideally at an early-stage startup where you’ve owned outcomes end-to-end.

-
You are a builder at heart. You don't need someone else to write the spec.

-
You've tinkered with a new model within days of its release, and you can explain why one architecture or approach is superior to another.

-
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)

While we appreciate your interest and application, due to the volume of applications we receive, only applicants under consideration will be contacted.

Please note: Jerry .ai is only able to hire full-time salaried employees who currently reside in AZ, CA, CO, FL, GA, IL, MA, NC, NJ, NV, NY, OR, TN, TX, UT, VA, or Ontario, Canada, and full-t