SlipstreamJobs tracks this role from the company's public career site. Apply directly on the employer's site.
Jerry.ai is a profitable, Series C, YC-backed fintech startup with 5M+ customers and $240M in funding. The company is building an AI-powered advisor to manage physical assets, starting with car insurance and expanding into home, motorcycle, RV, and other verticals. The business has achieved significant automation: 60% of insurance policies are sold automatically without human intervention, and 78% of inbound customer inquiries are resolved via AI and automation.
You will own the AI agents and automation system that powers Jerry's core insurance marketplace and customer experience. This includes two main components:
1. Agentic/conversational front end: chatbot, voicebot, and computer-use agents. You'll shape the prompt engineering team's direction and maintain sound architecture as the system scales.
2. Backend workflow automation: build new automations for document validation (driver's licenses, proof of insurance), record disputes, and transaction orchestration with external carrier systems.
Key responsibilities include evaluating emerging AI technologies (voicebot, computer-use agents, and beyond), making investment decisions on what to build next, and shipping to production. You'll partner with OpenAI to evaluate and deploy next-generation voice models and workflow automation capabilities.
The technical challenge is significant: Jerry's insurance marketplace is the core product and primary differentiator. Before off-the-shelf AI agents existed, the company built proprietary infrastructure to scale automated insurance purchases. Now, as business use cases expand beyond car insurance and AI models evolve rapidly, you'll lead building the next-generation AI system.
Tech stack: TypeScript (Nest.js, React), GraphQL, AWS (ECS/EKS, Lambda), and LLM models (OpenAI, Anthropic Claude, Google Gemini).
Note: The posting indicates flexibility on job title and leveling; Jerry is hiring one person and prioritizes finding the right fit.
REQUIREMENTS:
- 5+ years in software engineering, ideally at an early-stage startup where you've owned outcomes end-to-end
- Builder mentality; you don't need someone else to write the spec
- Experience tinkering with new models within days of release and explaining why one architecture or approach is superior to another
- Production experience with LLM-based systems, including evals, regressions, latency, cost optimization, and failure-handling
