ML Runtime Engineer

Join Loft, a fast-growing space technology company, as an ML Runtime Engineer. In this role, you will own model compilation, build the ground-side compile and delivery path, and contribute to the Space Inference Engine and SDK. You should have strong C++ and Python skills, experience with model compilation and embedded/edge GPU deployment, and familiarity with benchmarking and profiling. Benefits include equity, up to 35 days of paid time off, health and life insurance, lunch vouchers, cross-office travel opportunities, company and team off-sites, and relocation assistance to Toulouse when applicable.

• Model compilation: turn partner ONNX models into optimized engines per accelerator (TensorRT, Hailo, AMD/ROCm).
• Build the ground-side compile & delivery path; define how a mismatched engine is detected/rejected on-node.
• Build performance tooling: benchmarking, profiling, operator-coverage matrices, and budget validation.