Senior Reinforcement Learning Engineer

About the role

Gravis Robotics is a startup that turns heavy construction machines into autonomous robots. 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. Our team has over a decade of academic experience honing the cutting edge of large-scale robotics, and is rapidly growing to bring that expertise into a trillion-dollar industry through active deployments with market leaders.

The autonomy team at Gravis builds autonomous systems for excavators operating in real construction environments. You will build control modules that run on many different machines, across many sites, with different soil conditions. We’re looking for a roboticist with data-driven planning and/or control background, deep Python expertise, and good C++ proficiency. To be successful in this role you should have experience working with real robots, tackling the challenges of sim2real transfer, and deploying robotic systems in a production environment.

Responsibilities

• Develop data-driven planning and control systems for autonomous excavation that generalize across machine models and soil conditions
• Contribute to simulation improvements that reduce or address the sim2real gap
• Define data collection and curation pipelines for incorporating real data in policy training
• Design experiments focused on continuous performance and robustness improvements
• Explore the usage of adaptive and online reinforcement learning in deployed systems
• Provide mentorship and supervision for junior team members, interns, and students
• Integrate learned components into a larger software stack
• Collaborate with excavation and motion planning engineers
• Build tools for analyzing and evaluating the behavior of learned components

Requirements

• 2-5 years industry experience developing Reinforcement Learning systems for control and/or planning and deploying them on real robots with a customer (experience limited to simulation is not a fit)
• Experience with GPU-accelerated simulation environments (e.g., IsaacSim/IsaacLab, CARLA, MuJoCo)
• Strong Python skills and experience with PyTorch or similar libraries
• Proficiency in C++
• Comfortable debugging real-world system behavior
• Ability and willingness to travel as required by business projects

Nice-to-have skills

• Experience with hydraulic machinery
• Experience with supervised learning or imitation learning
• Research experience in reinforcement learning
• Experience deploying robotic systems at scale (e.g., hundreds of units)
• Familiarity with ROS or similar robotics frameworks
• Experience with feature-flagged deployments, staged rollouts, or long-lived platforms
• Experience with data curation for ML applications
• Experience guiding, mentoring, or leading junior colleagues, students, or project teams
• Familiarity with or interest in utilizing AI coding tools

Why this role is a great fit

• You are passionate about building systems that work reliably in the real world
• You want to help build a long-lived excavation planning and control system intended to scale and positively impact the entire construction industry
• You are comfortable working with the realities of imperfect data and noisy measurements
• You have a keen interest in bridging the sim2real gap and understanding the differences between simulation and physical environments
• You are excited to help drive technical direction in a growing team transitioning from prototyping to the product stage
• You value a collaborative team culture rooted in thoughtful design, creative thinking, mutual respect, and pragmatism

Benefits

Gravis Robotics offers a fair market salary and a working location in the vibrant city of Zurich. As a forward-facing startup, we understand that work-life balance and flexibility are important considerations for many professionals. If you are a highly qualified candidate with the requisite skills and experience, we encourage you to apply and discuss your preferred working arrangement during the interview process.