Clera
ML Engineer - Robotics
About this role
Join a robotics AI team to develop machine learning models that power perception, planning, and control systems for autonomous robots. You'll work across computer vision, sensor fusion, and reinforcement learning while integrating models into real-world robotics stacks in a fast-paced, collaborative environment.
What you'll do
- Develop and optimize ML models for perception, motion planning, and control systems
- Build computer vision and sensor fusion pipelines using camera, LiDAR, and IMU data
- Integrate learning-based models with ROS/ROS2 robotics software stacks
- Design data collection, simulation, and reinforcement learning workflows
- Deploy and validate models in live robotic environments alongside hardware engineers
- Evaluate model performance and robustness across diverse real-world scenarios
What they're looking for
- Python and C++ programming
- PyTorch and/or TensorFlow
- ROS/ROS2 integration
- Computer vision and sensor fusion
- Robotics simulation tools (Gazebo, Isaac Sim, CARLA, MuJoCo, PyBullet)
- Reinforcement learning and imitation learning
- Perception and motion planning pipelines
- Real-world deployment and robustness testing
Benefits
- Base salary $220,000–$300,000 USD annually
- Work on frontier AI and embodied intelligence problems
- Collaborate with frontier AI researchers and hardware engineers
- Fully on-site role in Mountain View, CA
Opens the application — the Jobs AI extension fills it for you. Set up autofill
Opens the official application on the employer’s site. No login required.
Clera
Clera builds an agentic operating system that automates complex workflows and processes through AI agents, with a platform designed to simplify distributed infrastructure management for developers. The company is hiring Founding Engineers, Customer Engineers, and Product Engineers to develop both backend systems and user-facing interfaces across their AI automation products.
View all jobs at CleraLikely interview questions
- Walk us through a perception or planning system you built end-to-end, from data collection to deployment on a real robot.
- How have you handled the gap between simulation performance and real-world robotic behavior, and what techniques did you use to improve robustness?