Machine Learning Engineer, Edge AI
Core
Lead the integration and control of next-generation AI accelerators, defining the firmware layer between high-level AI frameworks and custom silicon to manage DSP scheduling and data feeding for ultra-low-power targets.
Role type
Senior IC machine learning engineer (edge AI & embedded systems)
Builds
Production-ready edge AI systems for low-power 1D sensor processing and high-dimensional sensing systems like ultrasonic arrays
Domain
Edge AI, embedded machine learning, custom silicon hardware orchestration
Deliverable
production ML models
Required skills
Python, PyTorch, ONNX, CNNs, Transformers, state-space models, model quantization, pruning, graph optimization, kernel acceleration, hardware-aware training, DSP programming, DMA transfer management, memory tiling, latency optimization, power consumption optimization
Preferred skills
CUDA development, GPU optimization, TensorRT, ONNX Runtime, TVN, IREE, TinyML, embedded inference runtimes, multimodal AI systems
Technologies
PyTorch, ONNX, CUDA, TensorRT, ONNX Runtime, TVN, IREE, DSPs, GPUs, microcontrollers
Responsibilities
Lead R&D in edge AI and embedded ML; Design, train, evaluate, optimize, and deploy ML models for sensing applications; Investigate novel architectures for constrained edge deployments; Optimize AI workloads via quantization, pruning, and hardware-aware training; Deploy models across onsemi and third-party edge hardware; Translate research concepts into production-quality systems; Co-design AI solutions with hardware, firmware, and software teams
Seniority
Senior, hands-on IC
