Clera
ML Engineer – Robotics
About this role
A Series A robotics AI/ML company seeks an ML Engineer to develop and deploy machine learning models for autonomous systems, including perception, planning, and control pipelines. You'll integrate learning-based models with ROS/ROS2 stacks, work with sensor data, and collaborate with robotics engineers to validate systems in real-world environments.
What you'll do
- Develop and optimize ML models for perception, motion planning, and robotic control
- Build computer vision and sensor-fusion systems using camera, LiDAR, and IMU data
- Integrate learning-based models into ROS/ROS2 robotics software stacks for live deployment
- Design data collection, simulation, and reinforcement learning pipelines
- Deploy and evaluate models in real-time or embedded environments
- Collaborate with robotics and hardware engineers on system integration and testing
What they're looking for
- Python and C++
- PyTorch or TensorFlow
- ROS/ROS2
- Computer vision and sensor fusion
- Reinforcement learning or imitation learning
- Robotics simulation (Gazebo, Isaac Sim, CARLA, MuJoCo, PyBullet)
- SLAM, localization, and control systems
- Model deployment for embedded/edge devices
Benefits
- Base salary $220,000–$300,000 USD annually
- Remote-friendly work arrangement
- Collaborate with cross-functional engineering teams
- Work on cutting-edge autonomous systems
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 robotics project where you deployed an ML model end-to-end—what were the biggest challenges integrating with ROS?
- How do you approach training perception models that generalize across diverse real-world scenarios?