Staff Software Engineer (AI Agents)
About The Position
Traba is building an AI operating system for the industrial supply chain. The Staff Software Engineer (AI Agents) will be a founding member of the Agents team, leading development of Traba’s agentic platform: the layer that synthesizes marketplace data, connects with customers’ operational systems, and acts within facility workflows. The role owns the agents, evaluations, and model strategy that Traba’s products depend on, while partnering with the CTO on core architectural decisions, quality and reliability standards, and the platform roadmap. The engineer will architect the agent platform end to end, including the orchestration runtime, evaluation and observability stack, integrations with internal and customer systems, and reusable patterns for building agents. The role combines hands-on technical leadership with customer and operator engagement, hiring and mentoring engineers, and shaping repeatable deployment practices. It calls for an entrepreneurial leader comfortable with early-stage ambiguity who has built production agent systems and can make informed choices among prompting, fine-tuning, retrieval, and code.
Requirements
- At least 7 years of software engineering experience, including at least 2 years of hands-on production work on LLM- or agent-based systems.
- Deep experience with Python and/or TypeScript/Node.js.
- Track record designing distributed systems, APIs, and data models using PostgreSQL and modern messaging such as Kafka, RabbitMQ, or equivalent.
- Demonstrated ownership of a substantial production agent system, including orchestration, tool use, retrieval, evaluations, observability, and cost and latency tuning.
- Experience that maps to at least one of the following: a vertical AI or AI-agent company, a forward-deployed engineering role, or an AI-native data company.
- History of leading 0-to-1 builds in early-stage environments and comfort with ambiguity and high agency.
- Strong written and verbal communication skills, including ability to run customer workshops, write design documents, and recruit teammates.
- Ability to learn customers’ operational workflows, including WMS practices, shift cadence, and exception handling, and use that understanding to inform architecture.
Nice To Haves
- Supply chain, logistics, or industrial experience.
- Experience choosing foundational tools, integrating model providers, designing evaluation infrastructure, and leading by building working examples.
Responsibilities
- Architect Traba’s agent platform end to end, including its orchestration runtime, evaluation and observability stack, integration layer for internal and customer systems, and reusable agent-building patterns.
- Own foundational technical decisions around model strategy, harness design, retrieval and memory architecture, tool/MCP surface, and quality measurement.
- Spend time with customers and operators in the field and translate observations into durable product and repeatable deployment patterns.
- Build evaluation practices and infrastructure, including datasets, graders, regression suites, and experimentation tooling.
- Hire and mentor engineers and establish engineering quality standards.
- Partner with the CTO, product, and operations leadership on the multi-year platform roadmap.
Benefits
- Start-up equity.
- Competitive salary.
- 100% paid health, dental, and vision coverage.
- Dinner via DoorDash, free DashPass, and a stocked kitchen for New York employees.
- Commuter benefit.
- Gympass benefit.
- One Medical membership.
- HSA via Optum.
- Talkspace.
- HealthAdvocate.
- Teledoc Health.
Stand Out From the Crowd
Upload your resume and get instant feedback on how well it matches this job.
What This Job Offers
Job Type
Full-time
Career Level
Senior
Education Level
No Education Listed
