Applied AI Engineer, Agentic Systems

## **Role Description** As an Applied AI Engineer at ShipBob, you will lead the shift from manual workflows to autonomous operations. You won’t just be building chatbots; you will be architecting agentic systems that reason, use tools, and execute complex business logic independently. This is an "AI-First" engineering role where you will embed directly with business teams to map out operational friction and rapidly deploy end-to-end agentic solutions. From designing multi-agent orchestrations to building the "glue" code that connects LLMs to our core logistics APIs, you will be responsible for operationalizing AI at scale. We are looking for a high-agency builder who thrives in ambiguity and is obsessed with the transition from "software that waits for input" to "agents that take action." ## **Who You Are** * **You're a first-principles thinker and meta-learner.** The only constant in this role is change. You'll context-switch across projects and domains many times a month. Ambiguity doesn't slow you down. You make progress fast even with unclear requirements and moving targets. * **You optimize for surface area of technical skills, not depth in one stack.** If you have a favorite framework you've been married to for years, this probably isn't the role. We're looking for someone who gets genuinely excited when they have to learn a new API, pick up an unfamiliar tool, or dive into a platform they've never touched. You'll context-switch across different technologies constantly and that should energize you, not drain you. * **You write most of your code with AI.** You spend your coding time prompting Cursor, Claude Code, or Codex. You can manage multiple AI coding sessions simultaneously. You understand AI's limitations and own correctness and security. * **You love prototyping and shipping fast.** You've either done a lot of hackathons or built personal projects that solved real problems. Be prepared to share them—we'll talk about them a lot. You're a scrappy builder who can take an idea from 0→1 faster than most could write a PRD. * **You're relentlessly pragmatic.** You make smart tradeoffs to get value out quickly, then iterate once you know what matters. You're excited to work in messy, high-constraint environments: legacy codebases, enterprise infrastructure, incomplete documentation. * **Bonus: Founder background.** You've shipped and scaled products before. You think like a founder and challenge assumptions to deliver impact. **What you’ll do:** * Architect Agentic Workflows: Design and implement autonomous agents capable of handling multi-step reasoning, tool-calling, and error recovery. * Operational Discovery: Embed with logistics and support teams to identify high-impact opportunities for agentic intervention. * End-to-End Ownership: Own the entire agent lifecycle: Discovery → Agent Architecture → Prompt Engineering/Fine-tuning → Hardening → Production Deployment. * Build for Reliability: Develop robust guardrails, evaluation frameworks, and logging systems to ensure agents perform predictably in a high-stakes supply chain environment. * Contribute to the "Agent Hub": Document and publish reusable agent modules and toolsets to accelerate AI enablement across the entire organization. * Rapid Iteration: Bridge the gap between "cool demo" and "production tool" by shipping small, gathering feedback from domain experts, and iterating fast. **What you’ll bring to the table:** The work we do at ShipBob is both challenging and rigorous, which means our environment isn’t the right fit for everyone, and that’s okay. We welcome energetic high performers who thrive in a dynamic, collaborative, results-driven environment. We value individuals who embrace accountability and humility, push boundaries, and are motivated by challenging work. Every team member, no matter their role or tenure, is expected to roll up their sleeves and tackle the complex problems we face in today’s global supply chain. **Key Skills:** * You think like a founder, thrive in ambiguity, and are excited to challenge assumptions to deliver impactful solutions. * Agentic Expertise: Deep understanding of modern agent architectures (e.g., ReAct, Plan-and-Execute) and orchestration frameworks (e.g., LangGraph, CrewAI, or Semantic Kernel). * Engineering Rigor: 1–3 years of software engineering experience (or a standout portfolio of agentic projects) with strong proficiency in Python and .NET. * LLM Proficiency: Hands-on experience with LLM APIs (OpenAI, Anthropic) and a proven ability to translate raw model outputs into structured, deterministic actions. * Systems Thinking: Experience building retrieval pipelines (RAG), working with vector databases, and designing clean APIs that agents can easily consume. * Full-Stack Mindset: Ability to build the lightweight dashboards and interfaces (Vue.js/React) necessary for humans to interact with and monitor your agents. * Bias for Action: You prefer a working prototype over a long slide deck. You are comfortable challenging assumptions to deliver impactful, automated outcomes. **Things to know** We're hiring this role on a contract basis with the opportunity to convert to full-time, think of it as a mutual try out. ## **About ShipBob** Every time you order something online and it shows up fast, there's a gnarly logistics problem someone had to solve. ShipBob is a YC '14 unicorn backed by SoftBank Vision Fund, Menlo Ventures, and Bain Capital, building the tech stack that makes that happen for thousands of brands, from scrappy DTC startups to household names. We run fulfillment centers across three continents, and we're building AI-powered systems that orchestrate inventory, automate warehouse ops, and ship millions of packages. If you want to work on problems where software meets atoms and stakes are real, come build with us.