8 months ago
Responsibilities
- Develop, implement, and validate advanced control and learning algorithms for real-world embodied robotic systems.
- Design and conduct experiments to improve control robustness, precision, and adaptability across tasks and environments.
- Combine classical and learning-based control methods, including MPC, imitation learning, and reinforcement learning, for scalable skill acquisition.
- Collaborate with perception and systems engineers to integrate AI control stacks into production platforms.
- Use simulation, digital twins, and expert demonstrations to accelerate control policy development and deployment.
- Stay current with research in control theory, reinforcement learning, and embodied AI.
Requirements
- At least 5 years of industry experience.
- Proven experience delivering production-level robotic control systems in real-world deployments, such as autonomous vehicles, manipulators, humanoid robots, or mobile robots.
- Strong foundation in modern control techniques, including MPC, adaptive control, and system identification, and their integration with learning-based methods.
- Deep understanding of reinforcement learning, imitation learning, and optimization for dynamic systems.
- Proficiency in Python and familiarity with C++ for real-time robotics applications.
- Experience with high-fidelity simulators such as Isaac Sim, Omniverse, or MuJoCo.
- Strong communication and teamwork skills, including the ability to bridge AI research and robotic systems engineering.
Categories
ML EngineeringRobotics
About AIM
AIM builds autonomy for heavy equipment, turning bulldozers, excavators, and loaders into AI-driven fleets for mining, construction, infrastructure, and defense operators. The company sells an autonomy platform combining software, machine controls, and ruggedized hardware, deployed on active jobsites to run large-scale earthmoving. Founded in 2021 and headquartered in Redmond, Washington, AIM is privately held and backed by investors including General Catalyst and Khosla Ventures.