Senior AI Systems Architect

Jerry.ai•New York, NY

3d•$160,000 - $210,000•Remote

About The Position

Join a YC-backed, profitable Series C startup with capital and over 5 million customers. This role offers the opportunity to own the AI systems layer of a consumer product used by millions, focusing on LLMs, agents, and internal APIs applied to a fragmented $2T market. You will work with partners like OpenAI to integrate Jerry.ai services directly into the ChatGPT App and pioneer new model capabilities. The company has a flat organization, ambitious goals, and a direct line to the founders and execs. The technical challenges lie in the system architecture around AI, including agent capabilities, system integration, guardrails, and handling non-deterministic outputs. Jerry.ai is building the first AI-powered advisor to manage all physical assets, starting with cars and expanding into new verticals like home, motorcycle, RV, and boat. The company has a proven track record with its own infrastructure automating sales and service conversations, handling over 50,000 chats a month. This role requires someone to manage a fast-moving, high-volume chatbot operation and contribute to future bets in voicebot, computer use, and consumer AI applications.

Requirements

Systems designer: thinks in interfaces, failure modes, and blast radius; has redesigned something messy rather than working around it.
Fluent in modern AI: reads release notes for new models and has built with them.
Pragmatic: knows when to build the durable thing and when to ship the version that works this quarter.
5+ years in a product engineering or forward deployed engineering role, ideally in an early-stage startup.
A track record of turning ambiguous problems into systems that actually run.
Hands-on experience putting LLM-based systems into production, including evals, regressions, latency, cost, and failure handling.

Responsibilities

Decide what we build next in AI, and make the case for it.
Partner with OpenAI to evaluate and deploy next-generation voice models and workflow automation.
Evaluate emerging AI technology (voicebot, computer use agents, and beyond), prototype what's worth building, and make the call on what we invest in next.
Design evaluation frameworks and guardrails, and make the real tradeoffs between latency, cost, and accuracy in a regulated production environment.
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).
Work directly with subject matter experts to turn domain knowledge into systems that behave correctly.