Lead Software Engineer, Agentic Engineering

What You'll Do

• Lead the technical delivery of a workstream — own the design and implementation of production agents and the services they depend on, from prototype to production.
• Set and uphold engineering standards — agent patterns, tool integration, testing, code quality, and observability practices that hold the bar high on your part of the platform.
• Build the agent platform hands-on — implement the shared services and protocols (e.g., agent-to-agent messaging, tool servers) that let agents discover and compose with one another reliably.
• Stay deep in the code — you spend most of your time writing code, prototyping hard problems, and pairing with engineers on the toughest parts of the system.
• Help ensure agents behave — build the testing, evaluation, and observability that verify agents stay accurate, cost-efficient, and within guardrails over time.
• Mentor and review — guide engineers through design reviews and code reviews, and unblock them on hard technical problems.
• Break work into shippable increments — translate architectural direction into a plan you and the engineers around you can execute and be proud of.

What Differentiates This Role

• This role asks you to build autonomous systems that reason — agents that make decisions, call tools, and message one another.
• You're implementing how agents get built — the shared patterns, base abstractions, and "paved road" that make new agents fast to build and safe to run.
• You're responsible for knowing agents are behaving — observability, evaluation, and continuous checks, not a one-time test.
• You're working in non-deterministic systems — where correctness, cost, and safety all have to be designed in, not bolted on.

What You Will Bring

• 6+ years of software engineering experience with strong proficiency in Python and/or TypeScript.
• A track record of leading technical delivery — mentoring engineers, setting standards, and shipping complex systems.
• Experience building agentic or multi-step automated systems — tool orchestration, LLM reasoning loops, or agent frameworks.
• The ability to establish reusable patterns and technical direction that other engineers adopt.
• Experience designing for non-deterministic behavior, edge cases, and failure — and building the testing and observability to catch them.

Nice to Have

• Experience building LLM safety, evaluation, or governance systems.
• Retrieval / hybrid search over enterprise knowledge.
• Background in platform engineering or developer tooling at enterprise scale.
• Experience with AWS, GCP, or Azure.
• Terraform and infrastructure-as-code experience.
• Open-source contributions on public GitHub.

Work Environment

Hybrid work. Candidates must be located in the Farmington Hills / Metro Detroit, Michigan area. No remote candidates. Position not available for immigration sponsorship.