About this role
Staff AI Inference and Acceleration Engineer at Figure. Location: San Jose, California, United States. Role: owning architecture, mapping models, optimizing toolchains Requirements: MS/PhD or equivalent, 8+ years in hardware acceleration/ML systems, expertise in inference runtimes, quantization and pruning, profiling and benchmarking, model-to-hardware mapping, and strong C++/Python skills. Category: Engineering Seniority: Senior Level Tools: ONNX, TFLite, TVM, MLIR, TensorRT, Torch, SNPE/QNN, JAX, CUDA, ROCm, C++, Python Commitment: Full Time Workplace: Onsite Languages: English