Machine Learning / Robotics Engineer — Simulation

At Marvik, we’re looking for a Machine Learning or Robotics Engineer with experience in simulation to help us build AI solutions that interact with the physical world.

You’ll work on projects combining machine learning, perception, robotics, and simulated environments. We’re looking for a strong engineering foundation, hands-on simulation experience, and the flexibility to contribute across different industries and technical challenges as our projects evolve.

🧑🏻‍💻 What you'll do:

• Develop and evaluate machine learning and robotics solutions, from early experimentation to production integration.

• Build and use simulated environments to test algorithms, generate synthetic data, and evaluate system behavior.

• Develop pipelines for data collection, processing, training, and evaluation.

• Integrate models with sensors, software systems, and hardware when required.

• Design experiments to assess performance, understand failure modes, and measure how well simulation results transfer to real-world conditions.

• Collaborate with engineers, researchers, and clients to translate project requirements into practical solutions.

• Write maintainable code and contribute reusable tools and engineering practices across projects.

🤝 What we’re looking for:

• Professional experience in machine learning engineering, robotics, or a closely related field.

• Hands-on experience with a simulation platform such as NVIDIA Isaac Sim, Isaac Lab, MuJoCo, Gazebo, PyBullet, or a comparable tool.

• Strong Python programming skills and solid software engineering fundamentals.

• Experience developing and evaluating ML models or robotics algorithms, with a clear understanding of validation and performance metrics.

• Familiarity with relevant foundations such as sensor modeling, coordinate transformations, kinematics, dynamics, or physics-based simulation.

• Comfort working with Linux, Git, and collaborative development workflows.

• Ability to navigate open-ended problems, communicate trade-offs, and take ownership of implementation and validation.

🦾 It’s a major plus:

• Computer vision, 3D perception, or multimodal learning.

• Synthetic data generation, domain randomization, or sim-to-real evaluation.

• Reinforcement learning, imitation learning, motion planning, or control.

• ROS / ROS 2 and integration with physical sensors or robots.

• Deployment on edge devices such as NVIDIA Jetson.

• C++, GPU optimization, Docker, or cloud infrastructure.

• Experience bringing prototypes into reliable production systems.