Staff Software Engineer (AI Agents)

Traba•San Francisco, CA

5d•$240,000 - $300,000•Hybrid

About The Position

Traba is building the AI operating system for the industrial supply chain, focusing on automating manual workflows, deriving insights from data, and transforming decision intelligence for logistics providers, manufacturers, and 3PLs. The company aims to create a world where the global supply chain operates at peak efficiency and is backed by prominent investors. This role involves building the core AI agents, including harnesses, evaluation systems, orchestration, and model strategy, which form the foundation of Traba's product. The Staff Agent Engineer will be a founding member of the Agents team, leading the development of the agentic platform that synthesizes data, interacts with customer systems, and acts autonomously within operational workflows. The role requires a strong understanding of agent development, customer immersion, and data-product craft to build a 0-to-1 product.

Requirements

7+ years of software engineering experience.
2+ years of hands-on production work on LLM- or agent-based systems.
Deep expertise in Python and/or TypeScript/Node.js.
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.
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 skills—ability to run a customer workshop, write design docs, and recruit future teammates.

Nice To Haves

Bonus for supply chain, logistics, or industrial exposure.

Responsibilities

Build the AI agents themselves—the harnesses, evals, orchestration, and model strategy the rest of Traba's product runs on.
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.
Own the agents, evals, and model strategy that the Applied AI team depends on.
Partner with the CTO to make the core architectural calls on how agents are built, evaluated, and deployed at Traba.
Set the bar for quality and reliability for agent development.
Bring outside perspective on agent-building, FDE-style customer immersion, and data-product craft.
Architect Traba's agent platform end-to-end, including orchestration runtime, eval and observability stack, integration layer to internal and customer systems (WMS/TMS/ERP), and the patterns every agent is built on.
Own foundational technical decisions: model strategy, harness design, retrieval and memory architecture, tool/MCP surface, and quality measurement.
Spend real time in the field with customers and operators, translating observations into durable product and repeatable deployment patterns.
Build evaluation as a real engineering discipline, including datasets, graders, regression suites, and experimentation tooling.
Hire and mentor engineers, setting the standard for quality.
Partner with the CTO, product, and ops leadership on the multi-year platform roadmap.