Senior Software Engineer (AI Agents)

Join Traba, an early-stage startup revolutionizing the supply chain industry. As a Senior Software Engineer (AI Agents), you will build the AI agents that power our product, embedding deeply in our customers' operations and designing production agent systems on frontier LLMs. You will partner closely with our CTO, product team, and operators to take ideas from concept to scaled deployment. Enjoy competitive salary, equity, and comprehensive benefits.

• Concevoir et expédier des systèmes d'agents de production sur des LLM de pointe, y compris l'utilisation d'outils, de sous-agents, de récupération, de sorties structurées.
• Posséder l'évaluation en tant que discipline de première classe, y compris la conception de jeux de données, de rubriques et de notateurs, d'expériences et d'améliorations.
• Architecturer les données, les services et les API dont dépend la couche d'agents, en intégrant nos systèmes internes aux environnements WMS, TMS et ERP des clients.

• 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
• 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
• 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
• 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
• 5+ years of software engineering, with 1+ year shipping LLM- or agent-based features into production
• Excellent written and verbal communication—you can run a customer workshop in the morning and write a clean design doc in the afternoon
• A track record of building in fast, ambiguous environments—ideally at a vertical AI, AI-agent, forward-deployed, or data-product company
• 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