AI Embedded Engineer
Core
Deploy and optimize AI models (RL policies, vision, LLM) on custom robot platforms using edge hardware.
Role type
Mid–Senior Embedded AI Engineer
Builds
Real-time AI inference on Jetson-based onboard compute for custom robots
Domain
Robotics / Edge AI / Embedded Systems
Deliverable
production ML models
Required skills
C++, Python, ROS2, TensorRT, ONNX, Docker, NVIDIA Jetson deployment, systems optimization
Preferred skills
RL policy deployment, vision models, multimodal systems, real-time/safety-critical systems
Technologies
Jetson, TensorRT, ROS2, Docker, ONNX
Responsibilities
Deploy RL policies, vision models, and LLM components onto Jetson-based edge devices; Optimize inference performance (latency, memory, power); Integrate AI models into ROS2-based robotic systems; Build and maintain deployment pipelines using Docker; Debug and optimize AI workloads running fully onboard the robot; Collaborate with AI researchers and embedded software engineers.
Seniority
Mid–Senior, hands-on IC
