Staff Engineer, Embedded AI Software Engineer
Core
Designing and implementing next-generation embedded AI deployment infrastructure and model optimization tools for cutting-edge System-on-Chips (SoCs) to enable AI-based solutions on resource-constrained devices.
Role type
Staff Engineer, Embedded AI Software Engineer (Infrastructure & Tooling)
Builds
Production-quality embedded AI deployment infrastructure, model optimization pipelines, and hardware-aware tooling for ADI SoCs.
Domain
Semiconductor industry, Embedded AI, Hardware-Software Co-design
Deliverable
production ML models | infrastructure
Required skills
End-to-end AI/ML model development, Hardware-aware neural architecture design, C/C++/Python (firmware/low-level), Neural network quantization/pruning/optimization, Neural network accelerators (NPUs/DSPs), Embedded systems & computer architecture (bare-metal/RTOS/embedded Linux), Developer tooling (debuggers/profilers/SDKs)
Preferred skills
ARM Vela Compiler or Cadence XNNC, Hardware-software co-design, Neural architecture search (NAS), Digital signal processing (DSP), Agentic AI systems, FPGA development, Zephyr RTOS, Open-source ecosystems, Heterogeneous architectures (ARM/RISC-V/DSPs)
Technologies
TFLM, PyTorch, TensorFlow Lite, ONNX Runtime, TVM, MLIR, ARM, RISC-V, DSPs, NPUs, RTOS
Responsibilities
Design and implement novel AI model deployment tools for heterogeneous architectures (DSPs, NPUs, CPUs); Build end-to-end workflows for model development, optimization, profiling, and deployment; Develop tools for hardware-aware model design and architecture mapping; Design and implement model compilation and optimization pipelines (quantization, pruning, layer fusion); Prototype agentic AI workflows for automated model-hardware co-optimization; Develop company-wide strategy for production-quality embedded AI deployment infrastructure
Seniority
Staff, hands-on IC with strategic scope
