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. 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.

You'll build the AI agents themselves—the harnesses, evals, orchestration, and model strategy the rest of the product runs on. We're seeking an entrepreneurial Staff Agent Engineer to join as a founding member of the Agents team and lead the development of the agentic platform—the layer that synthesizes the data flowing through the marketplace, talks to customers' operational systems, and acts autonomously inside the workflows that run their facilities. You will partner with the CTO to make the core architectural decisions on how agents are built, evaluated, and deployed; set the bar for quality and reliability; and bring perspective on agent-building, customer immersion, and data-product craft.

About You

• Built production-grade agent systems that survived real-world usage.
• Shipped LLM/agent systems at scale, owning harness design, orchestration, evals, and on-call.
• Strong judgment on prompting vs. fine-tuning vs. retrieval vs. code.
• Comfortable learning operational domains (WMS quirks, shift cadence, exception handling) and shaping architecture accordingly.
• Sets direction by shipping canonical implementations and selecting foundational tools and model providers.
• Strong opinions on eval datasets, prompt versioning, and observability for agents.

You Will

• Architect the agent platform end-to-end—orchestration runtime, eval and observability stack, and integrations with WMS/TMS/ERP systems.
• Own model strategy, harness design, retrieval and memory architecture, tool surface, and quality measurement.
• Work directly with customers and operators to translate operational insights into durable product patterns.
• Build evaluation as an engineering discipline—datasets, graders, regression suites, and experimentation tooling.
• Hire and mentor engineers while setting standards for quality and reliability.
• Partner with leadership on the multi-year platform roadmap.

You Have

• 7+ years of software engineering experience, including 2+ years building production LLM- or agent-based systems.
• Deep expertise in Python and/or TypeScript/Node.js.
• Experience designing distributed systems, APIs, and data models using PostgreSQL and modern messaging systems (Kafka, RabbitMQ, or equivalent).
• Ownership of production agent systems including orchestration, tool use, retrieval, evaluation, observability, and cost/latency tuning.
• Experience in vertical AI, AI-agent companies, forward-deployed engineering, or AI-native data environments (supply chain/logistics exposure is a plus).
• Track record of leading 0-to-1 builds in early-stage environments.
• Strong written and verbal communication skills.

Benefits

• Start-up equity.
• Competitive salary.
• 100% paid health, dental, and vision coverage.
• Dinner provided via DoorDash, free DashPass, and stocked kitchen for NY employees.
• Commuter benefit.
• Gympass benefit.
• Additional benefits: One Medical membership, HSA via Optum, Talkspace, HealthAdvocate, Teladoc Health.

Salary Range Details

The compensation range for this position is $240,000 to $300,000, with potential exceptions for candidates whose qualifications significantly differ from those outlined.

Equal Opportunity Employer

The company evaluates all applicants without discrimination based on legally protected characteristics and encourages applicants from diverse backgrounds, experiences, and skill sets.