Agentic Integration Engineer — Scheduling & Fleet

About the Role

Intuition is a Silicon Valley robotics startup backed by some of the most prestigious investors in tech, connected to Founders Fund, MiniMax, Raspberry Pi, and others. Our team has backgrounds from Stanford University, UC Berkeley BAIR, Fudan AI, CMU Robotics Institute, and Google, and we work with industrial partners including KUKA, UR, Midea, Mercedes Benz, P&G, IKEA, and SF Express Logistics.

You'll join the Rapid Prototyping team at our Shenzhen deployment center: robots from many vendors arrive with an application, we build the station platform around them, and the solution ships. Every station shares one platform: a height-adjustable torso, two arms at ALOHA spacing, a top-view neck camera, fish-eye wrist cameras, a mid-height torso camera, and one Jetson Orin. V0 is a stationary single-arm station; V1 adds the second arm, one cable to the wall, and wheels that lock solid; V2 goes mobile with wheeled navigation, battery, and 5G.

You'll build Intuition's first robot-to-human experience: the way a customer hands a robot a job and gets it back finished. The deployment center is built for applications like boxes to pack, towels to fold, fruit to pick, surgical tools to clean, or lab samples to prep. Once a station does the work, someone at that factory, lab, hotel, or farm has to hand it the next job and know when it is done. You'll understand the end customer's API and build the customer-facing interface for scheduling jobs onto the robot. That interface is what the customer touches; the station behind it just runs.

Everything you build points at the ISS, the Intuition Scheduling System. Jobs come in from customers, stations and robots do the work, and the ISS will decide which station runs what, and when. Under it sits the fleet. In V1 the fleet is stationary: dual-arm stations, each on one Jetson Orin and one Ethernet cable to the internet. You build the fleet management for them: which station is free, which is running, which has stopped, and why. In V2 the fleet moves: robots on battery and 5G, navigating a mapped site to pick fruit, and mobile fleet management becomes critical. You build both, and for V2 that means where each robot is on the map, how much battery it has, and whether its 5G link holds.

You'll sit next to the deployment engineers who make the model run on the robot; you make the job reach the robot and the result reach the customer. The profile is simple: you build the API and the interface on top of it, and Claude Code is how you build them. When the customer's work is unclear, you ask them rather than guess.

What You'll Do

• Build Intuition's first robot-to-human experience: the interface a factory, lab, hotel, or farm uses to hand a robot its next job.
• Read the end customer's API, pick the calls that matter, and connect them so a job on their side reaches our station.
• Build towards the ISS: every job queued, assigned to a station, and visible to the customer.
• Ship stationary fleet management for V1: every dual-arm station reports free, running, or stopped, so no job lands on a stopped station.
• Ship mobile fleet management for V2: robots on battery and 5G, navigating a mapped site, still taking their jobs from the ISS.
• Hold the deployment target: your integration is ready the day the robot is.
• Define with the deployment engineers how a job reaches the robot, and how done, failed, or waiting comes back.
• Use agentic coding tools like Claude Code as a core part of your workflow, from first API call to last commit.

What We're Looking For

• No hard prerequisites to apply: we hire on what you have built and shipped, not on titles.
• Full-stack: you have built an HTTP API, the database behind it, and the interface on top, with users on the other end.
• You read someone else's API docs and come back with a working integration, not a list of questions the docs already answer.
• Scheduling or queue systems: jobs, states, retries, and what happens when two jobs want the same robot or a station stops mid-job.
• Product sense: you sit with the operator, learn how work is handed off, and turn that into a screen they will use.
• Agentic coding tools like Claude Code or Codex are already your daily workflow.
• Based in Shenzhen or ready to relocate.
• Bonus: you have built a scheduling, dispatch, or fleet dashboard for robots, vehicles, or machines.
• Bonus: you have put a Jetson Orin or a similar Linux box on a network and kept a service running on it.
• Bonus: you have worked inside a factory, lab, or hotel operation and know how jobs move through it.

Why Join Us

Every robot that leaves the deployment center gets its jobs through something you built. You'll join a small new team where the customer side and the fleet are yours from day one, and the ISS is what you build towards. Interns earn uncapped project bonuses, and top-performing interns may receive full-time offers and the opportunity for stock options. Full-time pay is set individually, with equity case by case and accommodation included. Direct mentorship comes from UC Berkeley BAIR professors and researchers at Physical Intelligence. Some interns are encouraged to pursue open-ended exploration, letting their own strengths shape what they work on. If you want to build the interface between people and working robots, this is it.