Senior Software Engineer (AI Agents)

Traba•San Francisco, CA

4d•$200,000 - $240,000

About The Position

Traba is building the AI operating system for the industrial supply chain. We started by tackling labor, supplying industrial businesses with consistent, reliable temporary workforces, and quickly became the fastest growing staffing company in America. Since then, we've expanded our suite of AI agents to help logistics providers, manufacturers, 3PLs, and other industrial businesses fully automate their manual workflows, derive insights from their data streams, and transform their decision intelligence. Our mission is to build a world where the global supply chain operates at peak efficiency. We’re proud to be backed by some of the world’s best investors, including Founders Fund, Khosla Ventures, and General Catalyst. You'll build the AI agents themselves—the harnesses, evals, orchestration, and model strategy the rest of Traba's product runs on. We're seeking an entrepreneurial Senior AI Agent Engineer to join as a founding member of the Agents team and build the next layer of Traba's product—an agentic platform that synthesizes the data flowing through our marketplace and operates autonomously inside our customers' supply chain workflows. (Our Applied AI team puts these agents to work across the product; you own the agents and infrastructure they depend on.) You'll embed deeply in our customers' operations, design and ship production agent harnesses on top of frontier models, and turn what you learn in the field into durable product. You will partner closely with our CTO, product, and our operators to take 0-to-1 ideas to scaled deployments.

Requirements

5+ years of software engineering, with 1+ year shipping LLM- or agent-based features into production.
Strong in Python and/or TypeScript/Node.js, and comfortable designing APIs, distributed systems, and data models in PostgreSQL.
Hands-on with the modern agent stack: production-scale prompt engineering, evaluation frameworks, orchestration patterns, and frontier model APIs.
A track record of building in fast, ambiguous environments—ideally at a vertical AI, AI-agent, forward-deployed, or data-product company.
Excellent written and verbal communication—you can run a customer workshop in the morning and write a clean design doc in the afternoon.

Nice To Haves

Builder with an AI operator's instinct. You've shipped real product on top of LLMs—not just chat wrappers. You've designed agent harnesses, structured tools, written evals, and tuned prompts against production traces. You think in capability, reliability, and unit economics—not just whether the model says the right thing.
Domain-immersed. You enjoy time with the people who do the work—learning an industry's vocabulary, edge cases, and operational tempo—and let that shape what you build.
High-agency in ambiguity. Dropped into a fuzzy customer problem with a half-formed hypothesis and a deadline, you scope, build, evaluate, and ship without waiting for a spec.
Sweat both ends of the stack. You move between prompt iteration, eval design, backend services, and customer-facing UI in the same week, and you care about evals that catch regressions and traces that are easy to debug.

Responsibilities

Embed with customers and operators to understand how supply chains run today—then design and ship agents that take meaningful work off their plate.
Build production agent systems on frontier LLMs: tool use, sub-agents, retrieval, structured outputs, MCP servers, and the orchestration that ties them together.
Own evaluation as a first-class discipline—datasets from real traces, rubrics and graders, experiments, and improvements you can prove move the needle.
Architect the data, services, and APIs the agent layer depends on—integrating our internal systems with customers' WMS, TMS, and ERP environments.
Codify repeatable deployment patterns so each new customer rollout is faster than the last.