Software Engineer, Robot Learning & Interfaces - #45312

We are looking for an engineer to own the path from data collection to a working robot, together with the interface someone can use to drive it. You would integrate a robot learning stack (LeRobot, DAgger, RL) and the libraries around it into our distributed system, and own customer-facing capabilities from end to end: choosing the approach, making it work, and being there when it is demoed.

This role is for library and framework integrators rather than from-scratch builders. We value engineers who pick the right off-the-shelf piece and integrate it cleanly. The work spans ML pipelines on one side, real product UI on the other, and a distributed system in between. Show and tell is part of the job and we hire for people who naturally build toward something visible.

You will be part of a fast-growing cutting-edge robotics and AI team looking towards developing solutions to real world problems.

What you'll do

• Integrate robot learning libraries (LeRobot, DAgger, RL, ACT/diffusion policies, VLAs, Nvidia Isaac) into our training and deployment pipelines.
• Wire ML artifacts (W&B, HF Hub, GCS) and the surrounding tooling into the systems that actually run on robots.
• Own customer-facing capabilities from end to end: choosing the approach, making it work, and demoing it live.
• Build and improve the teleoperation and data-collection interfaces.
• Use simulation when it speeds things up and real robots when it does not.

What you bring

• A track record of integrating complex libraries and frameworks into working systems, including an understanding of their failure modes rather than only their happy path.
• Experience integrating ML libraries into real software systems (research code into something closer to production).
• Solid frontend skills, ideally React with TypeScript. You can ship a usable interface.
• A taste for distributed systems, and an understanding that the model is one component among many.
• A show-and-tell instinct. You build to demo rather than to spec.

Nice to have

• At least two years at a robotics, IoT, or in-field-devices company. We would like at least one person on the team to have this background.
• Experience with ROS2.
• Hands-on experience with LeRobot, DAgger, or RL.
• Experience with WebRTC, GStreamer, or other real-time, low-latency systems.
• Experience with WebXR or immersive teleoperation interfaces.
• Experience with robot simulation (Isaac, MuJoCo, or similar).
• Customer-facing experience in demos, on-site integration, or technical pre-sales.

Logistics

• Based in Lausanne or Rome.
• Salary band based on seniority.
• Schengen Area citizenship required.

A few notes on applying

• Please apply to one role only. If you see yourself fitting more than one, just mention that in your application — we'll consider you for all of them.
• Keep your application short and concise. We thank you for not making us read more than half a page.
• (Optional): Tell us about one prototype you built quickly, that wasn't perfect, and that you demoed to a customer (or another real user). How did you build this prototype? How did you define what to build? What shortcuts did you take? We are keen to hear your short story, but can also ask for it once your CV was short-listed.

Embodied AI is an equal-opportunity employer. We celebrate diversity and are committed to creating an inclusive environment for all employees.