We are looking for a Machine Learning Engineer with experience building and deploying perception and sensor-based ML systems in robotics or autonomous platforms. The role involves working across the full lifecycle of data, models, and deployment—from raw sensor streams to production-ready perception modules.

This is a great fit for someone who has worked with LiDAR, cameras, radar, IMUs, or multimodal pipelines, and who enjoys taking ML systems from prototype to field-tested reality.

🧑🏻‍💻 Key Responsibilities

Perception & Sensor Fusion

• Develop ML pipelines for multimodal sensor data (LiDAR, cameras, radar, IMU, etc.).

• Implement or support sensor fusion approaches (classical or ML-based).

• Build models and processing steps for perception tasks such as detection, tracking, mapping, or scene understanding.
  
  

Cross-Functional Collaboration

• Work closely with robotics engineers, software teams, and simulation teams to ensure seamless integration of ML perception modules.

• Contribute to design discussions involving sensing hardware, data capture strategies, and operational requirements.
  
  

Model Development & Deployment

• Train, evaluate, and optimize ML models for robotics perception under real-world constraints.

• Deploy ML components to diverse environments (edge devices, robotics stacks, cloud backends).

• Collaborate on performance tuning, latency improvements, and reliability enhancements.

🤝 If you have

• Experience working with robotics or autonomous systems.

• Hands-on work with LiDAR, cameras, radar, or IMU pipelines.

• Strong Python and ML fundamentals, with experience in at least one major framework (PyTorch, TensorFlow).

• Experience designing or maintaining sensor-based ML systems, including data preparation and evaluation.

• Understanding of model deployment in real systems (edge devices, robotics stacks, embedded platforms, or cloud).

🦾 It’s a plus

• Experience with sensor fusion frameworks, classical or ML-based.

• Familiarity with robotics middleware (ROS/ROS2), mapping, SLAM, or navigation stacks.

• Exposure to simulation tools (Isaac Sim, Gazebo, Unity, Webots).

• Experience improving performance of models under real-time constraints.

• Background working with safety, reliability, or high-availability systems.