Robotics Machine Learning Engineer

Exclaim Robotics GmbH; Zürich; Vor Ort; CHF 120.000 - 180.000; Vollzeit

Benefits dieser Stelle

Office dog

Zusammenfassung

Exclaim Robotics GmbH in Zürich is seeking its first machine learning engineer to shape the robotics stack for maintaining critical infrastructure. You will design training pipelines, start with simulation, and iteratively deploy to real hardware as you refine behavior in the real world.

You will curate data, run experiments, and contribute to a small, hands-on team. A university degree in robotics or ML and working knowledge of RL or imitation learning are expected.

Qualifikationen

• Bachelor’s or higher in robotics, ML, or closely related field.
• Proven ability to train policies for physical systems, in simulation or on hardware.
• Experience with RL or imitation learning and reward shaping.

Aufgaben

• Set up training, decide data collection, and manage experiments.
• Build and maintain the training pipeline with proper versioning and logging.
• Bridge simulation results to real hardware, validating policies on the robot.

Kenntnisse

Policy training

RL / Imitation learning

Training pipelines

Simulation

Data curation

Ausbildung

University degree in robotics or ML

Tools

Weights & Biases

Isaac Sim

MuJoCo

Jobbeschreibung

About Exclaim Robotics
We're a small robotics company building robots to maintain critical infrastructure, starting with data centers.
Compute density in AI data centers is skyrocketing, which is forcing changes to rack dimensions and cooling, and above all to power. Those changes make a rack a worse place for a person to work. Most of the data center is controlled remotely anyway, so the physical tasks that remain are small and very precise: replacing an optical network connector without dislodging its neighbors, reconfiguring copper wiring, and replacing NVMe drives exactly straight, all through a mess of cables. The robot has to be reliable enough that people trust it near a rack that costs millions of dollars.
We're in pre-seed, and everything is still being built: the team, the company, the robots. If that sounds exciting rather than worrying, this might be the right place for you!

What You'd Be Doing
You'd be our first machine learning engineer, and the plan you'd be carrying out, and arguing with, goes roughly like this. Train a privileged policy in simulation, where we know exactly where every drive bay and connector is. Distill it into something that only gets to see what the robot can see. Then close the gap on real hardware, with residual RL or with imitation from teleop demonstrations. Simulation comes first, because the robot arms are still on order.

Most of the work is the pipeline around that plan, and none of it exists yet. You'd set up training, decide what data gets collected and what gets thrown away, and keep experiments in a state where we can actually tell which change helped. Data curation is the part nobody puts in a job ad, and it is most of what makes a policy work.

Someone else will worry about making the policy run fast on the robot. You would still be expected to go and stand next to the robot and watch it fail, because that is where you find out what your training distribution was missing.

What You Need to Bring:

• You've trained a policy that controlled something physical, either a real robot or one in a robotics simulator. Show us a repo, a paper, or a video of it running.

• A university-level degree in robotics, machine learning, or something adjacent. If you've managed to teach yourself to fully understand research papers without one, still happy to talk.

• Depth in RL or in imitation learning: sim training and reward shaping, or diffusion policies, ACT, and behavior cloning from demonstrations. Both belong here, fine if you're only experienced with one.

• You can build the training pipeline yourself, data in and checkpoints out, with experiments tracked somewhere we can read them. Weights and Biases is fine, and so is whatever has replaced it by the time you read this.

• Comfortable in a simulator, Isaac Sim/Lab or MuJoCo or similar, including the unglamorous half of building scenes and randomizing them.

• You don't need to be a controls or systems engineer, but you do need to care whether the policy works on hardware rather than in a notebook.

You'd be a good culture fit for us if:

• You like working closely with a small team

• You can take on a task you have no idea how to do, and figure it out as you go along

• You're comfortable giving and receiving honest feedback

• You care more about the robot working than about being right

• You're good at figuring out what needs to be done and doing it, rather than waiting to be told what to do or asking for permission

• Having an office dog isn't a deal-breaker

• You think joining an early-stage start-up will be a fun adventure

Don't look like a typical robotics engineer? Non-traditional background? Good. We're not really traditional either.