ML Runtime Engineer: Edge AI Inference & Optimization

Loft Orbital in Toulouse is looking for a skilled engineer to join their team. This role requires expertise in model compilation, specifically turning partner ONNX models into optimized engines for accelerators like TensorRT, Hailo, and AMD/ROCm. The successful candidate will also build performance tooling and contribute to the Space Inference Engine.

Benefits include equity, up to 35 days of PTO, health insurance, lunch vouchers, and cross-office travel opportunities. Join us and be part of our success!