Lead AI Product Engineer

Job Description

Job Description

Join a well-funded, fast-moving technology company building the next generation of consumer products powered by AI Agents. This is a high-impact opportunity for a hands-on engineer who wants to build ambitious agent systems from the ground up, move quickly from prototype to production, and have real ownership over architecture, reliability, performance, and product outcomes.

You'll work at the intersection of multi-agent orchestration, agentic coding, LLM infrastructure, and production engineering, turning emerging AI capabilities into scalable products used by real consumers. The team is looking for entrepreneurial engineers who thrive in fast-paced environments, enjoy solving hard technical problems, and want their work to directly influence the direction of new products.

What You'll Do

• Build and operate multi-agent systems that plan, coordinate, and execute complex tasks across tools and services.
• Develop agentic coding workflows where agents generate code, run tests, create changes, and iterate autonomously within defined guardrails.
• Design orchestration layers for planning, supervision, evaluation, retries, state management, and long-running workflows.
• Build reliable backend infrastructure supporting agent execution, including queues, pub/sub, durable state, concurrency controls, and failure recovery.
• Instrument agent behavior across success, failures, latency, cost, retries, and human intervention.
• Partner closely with Product and Design to rapidly turn user problems into working AI products.
• Build reusable AI infrastructure and engineering patterns that accelerate future product development.

What We're Looking For

• Strong experience building and operating production LLM-powered applications or Agentic AI systems.
• Hands-on backend engineering with Python and/or Node.js, APIs, async services, and background workers.
• Experience with tool/function calling, structured outputs, prompt engineering, and agentic coding workflows.
• Experience building multi-step execution loops such as plan act evaluate retry, including state management and failure recovery.
• Strong distributed-systems fundamentals including queues, pub/sub, concurrency, durable state, idempotency, and rate limiting.
• Experience with agent evaluation, including automated scoring, regression testing, simulation, or human-in-the-loop evaluation.
• Experience with RAG, vector databases, retrieval, and persistent memory.
• Understanding of cost-efficient LLM execution, including model routing, caching, batching, and budget controls.
• Production cloud experience with AWS or GCP, Docker, and CI/CD.
• Exposure to emerging agent technologies such as MCP or similar protocols is a plus, but experience with every framework is not required.

Who You Are

You're an entrepreneurial, hands-on engineer who likes turning ambitious ideas into working products quickly. You move with urgency without sacrificing engineering quality, take end-to-end ownership, and enjoy experimenting with emerging technology while building systems that are reliable enough for production.

This is an opportunity to join a well-funded company with strong momentum and a great collaborative culture, where AI is central to what's being built rather than an add-on to an existing product. You'll have the autonomy to experiment, ship quickly, and help define how next-generation consumer AI products are engineered and scaled.