Software Engineer - Agent Delivery

About Pallet

Pallet is building AI Agents to transform the $12 trillion logistics industry, backed by $50M from investors including General Catalyst, Bessemer Venture Partners, and Bain Capital Ventures. Our mission is to automate the physical economy by creating the most reliable intelligence infrastructure for logistics.

Our agents excel at handling complex logistics workflows—scheduling, data entry, and load management—for Fortune 500 companies. But this is only the beginning. Our vision is to be the go-to answer for AI in logistics: from proprietary models to a suite of tools that turn messy business rules into production-ready context for LLMs.

We're positioned to build the next $10B company in logistics. Join us and work alongside leaders from Google, DoorDash, YC, and more to shape the future of logistics tech.

About the Opportunity

We’re hiring one of our first Agent Delivery Engineers—a role focused on building, deploying, and operating production AI agent systems inside some of the world’s largest logistics companies.

You’ll work directly with Michael (Agent Delivery Lead) and partner closely with core Engineering, Deployments, and Sales leadership to take AI agents from post-sale technical scoping through hardened production launch. This role owns the engineering work required to make agents real in customer environments: designing system integrations, implementing agent behavior, resolving complex edge cases, validating performance, and iterating alongside core Engineering to ensure reliability at scale.

This is a foundational role at Pallet. The Agent Delivery team sits at the intersection of product, platform, and real-world operations—and is responsible for turning sales wins into live, revenue-generating AI systems. The systems you build will directly shape Pallet’s agent architecture, deployment patterns, and long-term product direction.

How you will make an impact

• Engineer and ship production-grade AI agent systems for some of the largest logistics companies in the world—owning the full lifecycle from technical scoping and system design through production deployment and iteration.
• Translate complex, messy logistics workflows into robust agent architectures, designing and building AI agents that outperform manual, human-driven workflows in how they reason, act, integrate with customer systems, and operate reliably at scale.
• Design and evolve shared systems that power agent behavior, orchestration, validation, and deployment across customer environments.
• Design and implement deep integrations with customer infrastructure (TMS, WMS, ERP, CRM, billing and settlement systems) using APIs, webhooks, event-driven systems, and data schemas.
• Own production reliability and debugging, investigating failures across AI behavior, system integrations, and data pipelines, and working closely with research and platform engineers to resolve root causes.
• Shape the product itself by contributing directly to core features, tooling, and platform improvements when customer deployments surface gaps or new requirements.
• Work directly with customer technical and operational leaders, deeply understanding their constraints and using that insight to drive both implementation decisions and the evolution of Pallet’s agent platform.

Preferred Experience

• 2+ years experience building and operating end-to-end production systems, ideally in high-growth SaaS or AI-driven environments
• Strong technical fundamentals across APIs, authentication, data modeling, system integration patterns, and debugging complex systems
• A builder’s mindset with high ownership—you’re comfortable scoping ambiguous problems, moving quickly, and shipping durable solutions
• Experience working directly with customers or external stakeholders, translating real-world constraints into reliable technical systems
• Clear and effective communication skills across both technical and operational audiences—from frontline operators to engineering leadership
• Thrives in fast-moving, ambiguous environments, where requirements are incomplete and problems are discovered through execution

Our Tech Stack

• Backend: Node + TypeScript on Encore.dev. Event-driven design with message passing and queues. Hosted on GCP
• Database: PostgreSQL
• LLMs: OpenAI, Anthropic, Google for foundation models; fine-tuned models on Vertex AI
• Browser Automation: Playwright
• Frontend: Next.js + React + TypeScript. Hosted on Vercel
• Observ