Staff Software Engineer (AI Agents)

Required

• You've built agents that survived contact with reality. You've shipped agent systems into production at scale—designed the harness, picked the orchestration patterns, owned the evals, and lived with the on-call—and you have strong opinions on where to draw the line between prompting, fine-tuning, retrieval, and code.
• Domain depth meets technical breadth. You're as comfortable in a warehouse on a customer site as in a design doc—you learn an industry's actual operations (WMS quirks, shift cadence, exception handling) and let that shape architecture.
• Set direction by shipping. You raise the bar by writing the canonical example, not just the doc—picking the foundational tools, integrating the right model providers, designing the eval infrastructure, and bringing others along.
• Sweat the small stuff at staff scale. You have strong opinions on eval datasets, prompt versioning, observability for agents, and the line between a clean abstraction and an over-engineered one.
• 7+ years of software engineering, with 2+ years of hands-on production work on LLM- or agent-based systems.
• Deep in Python and/or TypeScript/Node.js, with a track record designing distributed systems, APIs, and data models on PostgreSQL and modern messaging (Kafka, RabbitMQ, or equivalent).
• Demonstrated ownership of a non-trivial production agent system: orchestration, tool use, retrieval, evals, observability, and cost/latency tuning.
• Background that maps to at least one of: vertical AI / AI-agent company, a forward-deployed engineering role, or an AI-native data company. Bonus for supply chain, logistics, or industrial exposure.
• A history of leading 0-to-1 builds in early-stage environments—comfortable with ambiguity and high-agency by default.
• Strong written and verbal communication—you can run a customer workshop, write the design doc, and recruit your future teammates.