Own Pilot.Auto’s release lifecycle by building backend services, CI/CD pipelines, automated release gates, and traceable build and test workflows for autonomous-driving software.
About this role
This Edge AI engineer deploys perception models on autonomous vehicles within TIER IV's Co-MLOps project. The work balances recognition accuracy and robustness against the heat, power and computing limits of in-vehicle hardware.
The engineer implements DNNs for GPUs, FPGAs and AI accelerators, develops lighter models for lower-cost and lower-power operation, and deploys Camera/LiDAR networks. Hardware characteristics and model design are optimized together so that perception models can run on vehicle systems.
Applicants need computer-architecture and machine-learning knowledge, DNN algorithm-development experience, and experience deploying to AI accelerators with frameworks such as NVIDIA TensorRT or AMD Vitis AI. Requirements also include model compression using techniques such as pruning, quantization or multi-task learning, and implementation of Camera or LiDAR DNNs.
This is an AI-generated summary of the employer's original posting — details can be incomplete, out of date or simply wrong. Always confirm everything on the official posting before applying.