Staff Software Engineer (AI Agents)

Traba is the AI operating layer for the industrial supply chain. We started in workforce—temp staffing, the biggest operational pain point for the manufacturing and logistics customers we serve—and used it to embed ourselves inside their daily operations and create a far better customer experience through technology. Now those same customers are pulling us beyond staffing into the broader operational workflows that run their facilities. That foundation gave us proprietary data from millions of shifts and deep enterprise relationships. But our edge is more than data: by connecting to the systems running across every facility and activating the workers already on our platform to execute against them, we are building applied AI that drives real productivity gains and transforms how the global supply chain operates at scale. We are backed by Founders Fund, Khosla Ventures, and General Catalyst.   We are seeking an entrepreneurial Staff Applied Agent Engineer to join as a founding member of the Agents team and lead the development of Traba's agentic platform—the layer that synthesizes the data flowing through our marketplace, talks to our customers' operational systems, and acts autonomously inside the workflows that run their facilities. You'll partner with our CTO to make the core architectural calls on how agents are built, evaluated, and deployed at Traba; set the bar for quality and reliability; and bring the outside perspective on agent-building, FDE-style customer immersion, and data-product craft that this 0-to-1 product needs.   ABOUT YOU - You've already built agents that survived contact with reality. You've shipped agent systems into production at meaningful scale—designed the harness, picked the orchestration patterns, owned the evals, and lived with the on-call. You have strong opinions on where to draw the line between prompting, fine-tuning, retrieval, and code, and why. - Domain depth meets technical breadth. You're as comfortable in a warehouse on a customer site as you are in a design doc. You learn an industry's actual operations—WMS quirks, shift cadence, exception handling—and let that knowledge shape architecture decisions. Ideal: prior experience at a vertical AI or AI-agent company (Nash, HappyRobot, Augment, Pallet, Harvey, Legora, ElevenLabs), Palantir/Scale-style FDE, or an AI-native data company (Hex, Omni, dbt). - Set direction by shipping. You raise the engineering bar by writing the canonical example, not just the doc. You pick the foundational tools, integrate the right model providers, design the eval infrastructure—and you bring others along. - Sweat the small stuff at staff scale. You have strong opinions on design patterns, eval datasets, prompt versioning, observability for agents, and the difference between a clean abstraction and an over-engineered one. You understand that how we do one thing is how we do everything. YOU WILL - Architect Traba's agent platform end-to-end—the orchestration runtime, the eval and observability stack, the integration layer to internal services and customer systems (WMS/TMS/ERP), and the patterns that every agent we ship is built on. - Own the foundational technical decisions for this part of the business: model strategy, agent harness design, retrieval and memory architecture, tool/MCP surface, and how we measure quality. - Spend real time in the field with customers and operators. Translate what you see into durable product and codify repeatable deployment patterns so each rollout compounds on the last. - Build evaluation as a real engineering discipline—datasets, graders, regression suites, experimentation tooling—so we ship agent improvements with the same confidence we'd ship backend code. - Hire and mentor the engineers who will build alongside you. Set the technical standards that define what “good” looks like for applied AI at Traba. - Partner with the CTO, product, and ops leadership on the multi-year platform roadmap. Think ahead to what the company and the agent layer will need a year or two from now, and start building it today. YOU HAVE - 7+ years of professional software engineering experience, with 2+ years of hands-on production work on LLM- or agent-based systems. - Deep proficiency in Python and/or TypeScript/Node.js, and a strong 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, cost/latency tuning, and the operational lessons that come with all of it. - Background that maps to at least one of: vertical AI / AI-agent company, Palantir/Scale-style FDE, or an AI-native data company (Hex, Omni, dbt). Bonus for supply chain, logistics, or industrial operations exposure. - A history of leading 0-to-1 product builds in early-stage environments—comfortable wit