Staff Software Engineer, Agents

Nominal•Los Angeles, CA

About The Position

Nominal's mission is to accelerate how the world engineers new hardware. Our connected test and operations platform powers the world's most advanced hardware programs and its most ambitious startups. We are expanding across the entire hardware lifecycle, building the foundation, AI-native applications, and agents that accelerate innovators' work and change what's possible to build. The Hardware Intelligence team is behind Nominal's agents, AI-native applications, and MCP, and its forward-leaning AI bets. Our mission is to unlock the bottlenecks of the hardware lifecycle with AI. Our agents reason over physical reality, from high-rate telemetry and test campaigns to designs and simulations, where real test results are the ground truth their work is checked against. We believe opinionated AI, built for the real work of hardware programs, will change how the world engineers. We're collaborative, iterative, and high-agency, and we're human-centered and customer-focused. We build with the newest AI tools every day, and because those tools keep changing, so do we: we stay curious and keep looking for the better way. Our team spans data science and ML, distributed systems, search, and knowledge systems, and we obsess over how agents can be genuinely useful to the engineers who rely on them.

Requirements

8+ years building production systems, including real experience shipping LLM or agent systems to users.
Strong distributed-systems and backend fundamentals; you've owned systems where reliability mattered.
Opinions about agent architecture (tool design, context management, autonomy, failure handling) and the judgment to change them when data says so.
A track record of setting technical direction across a team and raising the bar for the engineers around you.
You build with modern AI coding agents (Claude Code, Cursor, Codex) every day, and stay curious and open to better ways of working. The tools keep changing, and so do we.

Nice To Haves

You've built an agent harness or LLM platform that other engineers or customers build on, at an AI-native company.
You've shipped long-running, autonomous agents to production and know where they break.
You've contributed to MCP, agent frameworks, or open-source LLM infrastructure.
You've built software for physical systems: robots, vehicles, aircraft, or the test stands behind them.

Responsibilities

Design and build the agent harness: orchestration, planning, tool calling, memory, and background agents that run long investigations on their own.
Own the shared tool layer that our agents and external agents (via MCP) both use, so every capability we build works everywhere.
Build how agents assemble context: retrieval across test data, documents, designs, and simulations, including sensor data far too large to fit in a context window.
Make model choice a decision, not a dependency: routing, cost, latency, and fallbacks across frontier models.
Partner with evals to make quality measurable, and with the platform team on how the context layer grows.
Set the architecture other engineers build on, and raise the bar through design reviews and mentorship.