Staff Machine Learning/AI Engineer, Hardware
Core
Lead development of machine learning enablement workflows, compiler tooling, and model optimization for edge AI platforms and hardware accelerators.
Role type
Staff Machine Learning/AI Engineer (Hardware & Compiler)
Builds
Front-end compiler and model-ingestion tooling, quantization-aware training infrastructure, and optimized ML models for RAP1-class edge platforms.
Domain
Automotive / Edge AI / Hardware-Software Co-design
Deliverable
production ML models
Required skills
Machine learning systems, model deployment, compiler/toolchain development, model optimization (quantization, pruning), hardware/software co-design, low-power edge platforms, NPU/GPU architectures, memory allocation, execution scheduling, cross-functional leadership.
Preferred skills
Quantization-aware training, post-training quantization, vision/multimodal model deployment, ONNX and graph transformation pipelines, numerical validation across float/integer paths, startup/founder-level experience.
Technologies
RAP1, ONNX, NPU, GPU, C++, Python (implied by tooling context)
Responsibilities
Lead development of ML enablement workflows for edge AI platforms; Build and improve front-end compiler and model-ingestion tooling; Develop and scale robust quantization-aware training and model optimization infrastructure; Port, optimize, validate, and benchmark ML models for hardware accelerators; Improve performance across memory, scheduling, and data-movement constraints; Provide technical leadership and mentoring for engineers.
Seniority
Staff, technical leadership & strategy