About this role
ML Runtime Engineer at Loftorbital. Location: Toulouse, Occitanie, France. Role: compiling models, benchmarking performance, delivering engines Requirements: Strong C++ and Python; experience with model compilation (TensorRT or equivalent), ONNX/ONNX Runtime, quantization and inference optimization, embedded/edge GPU deployment (NVIDIA Jetson), benchmarking/profiling, and CI/CD with hardware-in-the-loop. Category: Software Development Seniority: Mid Level Tools: C++, Python, ONNX, ONNX Runtime, TensorRT, Hailo SDK, AMD ROCm, NVIDIA Jetson, CI/CD, Meson, Yocto, Debian, Space Inference Engine, OBSW Commitment: Full Time Workplace: Onsite Languages: English