Machine Learning Engineer - Sim2Real & Machine Modeling

1 мес. назад

ШвейцарияHybrid

lidargnssedge computing

Engineer focused on applying machine learning to physical AI for autonomous construction machinery.

Gravis Robotics is a high-growth Series A start-up backed by SoftBank, bringing Physical AI to the construction industry, turning heavy construction machines into autonomous robots. Gravis began as an ETH Zurich spin-out, and our unique combination of learning-based automation and augmented remote control lets one operator safely conduct a fleet of earthmoving machines in a gamified environment. Backed by deep robotics research and now deployed across multiple countries with leading construction and equipment partners, our team is rapidly growing to bring this technology to a trillion-dollar industry. The Gravis RACK is a machine-agnostic retrofit kit that adds autonomy to excavators and wheel loaders from 10 to 100+ tonnes: LiDAR and camera sensing, GNSS RTK, networking hardware and rugged edge compute that works offline. Paired with the Slate tablet and our Copilot software, it lets an operator run a machine manually, with AI assistance, or fully autonomously. Increasingly, we also build custom hardware to adapt our machines for highly specialized, robust applications beyond traditional excavation.

Autonomy team at Gravis heavily relies on simulation to develop autonomous controllers. Whether these controllers work on the machine depends on how well we close the sim2real gap. In this role you will help us bridge the gap. We are looking for someone with strong ML/RL background and experience with real robotic systems.
Build ML models to help bridge the sim2real gap
Decide what architecture the problem actually needs - sequence models, state-space formulations, something else - and back the choice with data
Characterize where the gap actually comes from: which unmodeled effects hamper the sim2real transfer, and which we can safely ignore
Answer how much data is needed and what distribution it has to cover
Define the performance metrics and validation methodology for model fidelity and sim2real transfer
Build models and methods that detect machine properties changing over time
Work closely with the autonomy and simulation teams — your models influence the controllers that run on the machine

Degree in Computer Science, Robotics, Machine Learning, Engineering, or a related field
Strong Python and PyTorch, strong git skills
Solid experience modeling time-series or dynamical-system data from large datasets - sequence models, system identification, or state-space approaches
Strong analytical skills: you design the experiment, run the ablation, and draw a conclusion you'd defend
Reinforcement learning experience
Imitation learning or learning from demonstration, especially from human operator data
Familiarity with recent literature and methods in learned behavior policies
Classical system identification, control, or hydraulics background
You like to solve problems outside of the laboratory
You like a culture where the best idea wins no matter whether it comes from the CTO or an intern, as long as it's backed by numbers
You are comfortable owning the result end to end: when the data you need doesn't exist yet, you go on site, touch the machine and get it
You'd take a simple model that measurably closes the gap over a sophisticated one that might, and you're patient enough to get there in steps