Fullstack Software Engineer, ADK

About Pelico

Traditional industrial manufacturing systems were built for predictability. Supply chains no longer are. Today, real-time data is buried in legacy tools that weren't designed for constant disruption. By the time an issue surfaces, it has already snowballed, sending everyone into firefighting mode. Pelico exists to close the gap between production plans and the daily reality on the factory floor.

We've built the manufacturing orchestration platform trusted by the world's most complex industrial operations : companies like Airbus, Boeing, Safran, Eaton, and Cartier. Our AI connects fragmented supply chain, production, and quality data into a single live operational picture — then puts AI agents to work anticipating disruptions, simulating recovery options, and keeping every team aligned before small problems become expensive ones.

Founded in 2019 and backed by General Catalyst, 83

North, and Serena, we've raised $72M and are growing fast — 300% year-over-year revenue growth, deployed in 15+ countries, and supporting factories worldwide. We're headquartered in Paris, with offices in Miami, London and Amsterdam, and we're just getting started.

This is a rare chance to join a company that's redefining an industry that hasn't been disrupted in decades — from the inside.

Companies have multiple founding moments and Pelico is going through a new one.

You would be one of the founding engineers of our new agentic platform, building alongside a small, super talented, high-bar team. This is a hands-on seat from day one: you write the code that manufacturers and their own AI teams build on, close to real customers and real factory data.

You benefit from company assets (data, events dependency graphs, simulation engine, next best action algorithms) and the reach that comes from Pelico running the operational data of multiple leading manufacturers.

• Ship agent capabilities end to end. Build real features from the tool/MCP and orchestration backend through to the React console, live for users - not demos.

• Harden the runtime. Durable execution, retries, scheduling, and human-in-the-loop approvals on agent actions that carry real consequences.

• Make agents trustworthy. Grow the eval harness (scenario evals, LLM-as-judge) so we catch regressions in agent behavior before they ship.

• Build a console people believe. Real-time streaming of agent events, tool calls, and approvals - clear, fast, and reliable enough that a controller trusts it.

• Set a craft bar. Write specs others build against, keep the frontend/backend contract honest, and leave reusable patterns the team adopts.

We care about how good you are and how far you can go, and we calibrate to the experience you bring. This seat is built for exceptional people - whether you are just out of a top program or already have a few years of serious building behind you.

• An excellent engineer who ships. You write excellent code and have built real things, full-stack across a Python backend and a React frontend - or you are clearly able to get there fast.

• Hungry and driven. You want a hard problem to own, not a comfortable seat, and you have the ceiling to grow into far more.

• Rigorous with non-deterministic systems. You spec and eval before shipping, trust evidence over vibes, and own what goes out - including AI-assisted code - following problems into production.

• AI-native and curious. You understand how agent frameworks, tools, and evals actually work under the hood, and you build with AI coding tools every day.

• Calm in fast-moving ambiguity. You stay effective on a stack where this quarter's best practice changes next quarter, turning uncertainty into a workable plan.

Nice to have: real AI/agent product experience (MCP, agent…