Senior Machine Learning Engineer - Sim2Real & Machine Modeling

About the role

The Autonomy team at Gravis Robotics is seeking a Senior Machine Learning Engineer to bridge the sim2real gap for autonomous construction machinery. You will develop machine and dynamics models, define performance metrics, and work closely with autonomy and simulation teams to ensure controllers function effectively on real-world equipment. This role involves designing experiments, analyzing large datasets, and validating model fidelity to improve autonomous performance.

Responsibilities

• Build ML models to bridge the sim2real gap and determine appropriate architectures based on data.
• Characterize unmodeled effects to understand and minimize the sim2real transfer gap.
• Define performance metrics and validation methodologies for model fidelity.
• Build models and methods to detect changes in machine properties over time.
• Collaborate with autonomy and simulation teams to influence controller development.

Required skills

• Python
• PyTorch
• Git
• Time-series modeling
• Dynamical-system modeling
• Sequence models
• System identification
• State-space approaches
• Experimental design

Nice to have

• Reinforcement learning
• Imitation learning
• Learning from demonstration
• Classical system identification
• Control theory
• Hydraulics

Qualifications

• Degree in Computer Science, Robotics, Machine Learning, Engineering, or a related field

About the Company

Gravis Robotics is a high-growth Series A start-up backed by SoftBank that brings Physical AI to the construction industry by turning heavy machinery into autonomous robots. Originating as an ETH Zurich spin-out, the company develops machine-agnostic retrofit kits that enable autonomous operation for excavators and wheel loaders.