Research Engineer (Robot Learning)

InLoop builds warehouse robots that run autonomously in customer warehouses today. The fleet is growing quickly (20+ robots), and we're scaling to hundreds of robots in the next months.

We're hiring a research engineer to speed up how fast our robots master new skills in the real world. You will build and run our data flywheel, making our policies faster and more reliable with every deployment hour. Customer feedback is the best benchmark, and with our fast validation loop, you will be able to drive improvement at speed.

What you'll work on

• Deployment research: Lead the research project to deploy 50+ robots in the months, working closely with our deployment team.
• Improve policy performance: Customers care most that the robot is fast and reliable. You'll make our policies both.
• Data flywheel: Design and manage the data flywheel from our deployed robots, from collection to training and evaluation.

What we're looking for

• Experience designing and fine-tuning robot foundation models (IL, RL).
• A rigorous approach to benchmarking and evaluation.
• You've trained and deployed policies on real robots.

Nice to have

• Experience making inference fast and robust across many robots
• RL, sim-to-real, or learned control experience
• PhD with a track record of publications (CoRL, RSS, ICRA, ICLR, CVPR, etc.)

How to apply

Apply here and include a link to a policy you trained running on a real robot, a paper, or a repo. That tells us more than a CV.