Senior Software Engineer (AI Agents)

Description

The company is building an AI operating system for industrial supply chains, covering the warehouses, manufacturers, logistics providers, and workers that keep physical goods moving.

It started by supplying temporary labor to industrial businesses and has grown quickly as a US staffing company.

Its AI agent suite now helps logistics providers, manufacturers, 3PLs, and similar firms automate manual workflows in full, pull insights from data streams, and sharpen decisions.

The goal is a global supply chain that runs at peak efficiency.

The company is venture-backed.

This is a founding role on the Agents team. The Applied AI team deploys these agents across the product, and you own the agents and the infrastructure beneath them, including harnesses, evals, orchestration, and model strategy.

You will work inside customers' operations, ship production agent harnesses built on frontier models, and convert what you observe in the field into lasting product. You will work with the CTO, product, and operators to take early ideas to scaled deployments.

Responsibilities

• Spend time with customers and operators to learn how their supply chains work, then build agents that remove real workload from them.
• Build production agent systems on frontier LLMs, including tool use, sub-agents, retrieval, structured outputs, MCP servers, and the orchestration connecting them.
• Run evaluation as a core practice: build datasets from real traces, write rubrics and graders, run experiments, and confirm that changes improve results.
• Design the data, services, and APIs the agent layer relies on, integrating internal systems with customer WMS, TMS, and ERP environments.
• Standardize deployment patterns so every new customer rollout takes less time than the one before.

Requirements

• You have an AI operator's instincts and have shipped real products on LLMs, not only chat wrappers. You have designed agent harnesses, structured tools, written evals, and tuned prompts against production traces. You reason about capability, reliability, and unit economics, not only whether the model answers correctly.
• You like working alongside the people who do the work, learning an industry's vocabulary, edge cases, and operating pace, and let that guide what you build.
• You can take a vague customer problem with a rough hypothesis and a deadline, then scope, build, evaluate, and ship without waiting for a detailed spec.
• You work across prompt iteration, eval design, backend services, and customer-facing UI, sometimes in the same week, and you care about evals that catch regressions and traces that are easy to debug.
• You have 5+ years of software engineering experience, including 1+ year shipping LLM or agent features into production.
• You are strong in Python and/or TypeScript/Node.js and comfortable designing APIs, distributed systems, and data models in PostgreSQL.
• You have hands-on experience with the current agent stack, including prompt engineering at production scale, evaluation frameworks, orchestration patterns, and frontier model APIs.
• You have built products in fast, unclear settings, ideally at a vertical AI, AI-agent, forward-deployed, or data-product company.
• You communicate well in writing and speaking, able to lead a customer workshop in the morning and produce a clear design doc in the afternoon.

Conditions

The base pay range for this role is $200,000 to $240,000, based on market data and other factors. Exceptions may be made for candidates whose qualifications differ significantly from those in the description.

Benefits

• Startup equity
• Competitive salary
• Health, dental, and vision coverage paid 100%
• Meals delivered through DoorDash, a free DashPass, and a stocked kitchen for New York staff
• Commuter benefit
• Gympass membership
• Additional perks: One Medical membership, Gympass, an HSA administered by Optum, Talkspace, HealthAdvocate, and Teledoc Health