Staff Engineer, Embedded AI Software Engineer

Job Title

Staff Engineer, Embedded AI Software Engineer

Role Summary

Design and implement embedded AI deployment infrastructure and model-optimization tooling for resource-constrained heterogeneous SoCs (DSPs, NPUs, CPUs). You will be a core member of the Embedded AI Tooling Team building end-to-end workflows that take models from development through optimization, profiling, and production deployment on ADI embedded platforms.

Work includes toolchain, compiler and code-generation components, hardware-aware model design, and collaboration with firmware and hardware teams to maximize AI performance on SoC platforms.

Experience Level

Senior (Experienced). Years of experience not specified in the posting.

Responsibilities

Primary responsibilities and expected deliverables.

• Design, implement, and ship AI model deployment tools and infrastructure for constrained heterogeneous architectures (DSPs, NPUs, CPUs) on embedded SoCs.
• Develop end-to-end workflows covering model development, optimization, profiling, hardware mapping, and deployment to embedded platforms.
• Create hardware-aware model design tooling, including architecture mapping, mixed-precision support, and optimizations such as quantization, pruning and layer fusion.
• Implement model compilation and optimization pipelines that produce hardware-specific code and enable efficient runtime on ADI platforms.
• Prototype agentic AI workflows for automated model-hardware co-optimization and architecture search.
• Lead technical strategy for production-quality embedded AI deployment tooling and act as a subject-matter expert across teams.
• Collaborate with firmware, low-level software, and hardware engineers; perform profiling and performance tuning; travel up to 10% as required.

Requirements

Key must-have skills and additional desirable skills.

• Must-have: Practical experience with end-to-end AI/ML model development, optimization and deployment on embedded devices; hardware-aware neural architecture design; proficiency in C, C++ and Python; firmware or low-level software development experience; familiarity with AI/ML frameworks and deployment tools (examples: TFLM, PyTorch, TensorFlow Lite, ONNX Runtime, TVM); strong understanding of quantization, pruning, knowledge distillation and other model compression techniques; knowledge of neural accelerators (NPUs, DSPs) and execution on heterogeneous hardware; embedded systems and computer-architecture experience (bare-metal, RTOS, or embedded Linux); background with ML architectures (CNNs, DNNs, Transformers).
• Nice-to-have: Experience with ARM Vela or Cadence XNNC compiler tools; hardware-software co-design and custom operator development; neural architecture search (NAS); DSP algorithm implementation; agentic AI or multi-agent optimization workflows; edge AI frameworks (TensorFlow Lite Micro, Apache TVM, MLIR); compiler optimizations and code generation for accelerators; FPGA development; Zephyr RTOS; open-source contributions.

Education Requirements

Not specified.

About the Company

Company: Analog Devices

Headquarters: Norwood, Massachusetts, USA

Analog Devices is a leading global semiconductor company that bridges the physical and digital worlds, enabling breakthroughs at the Intelligent Edge. With a focus on innovation, ADI develops solutions that drive advancements in digitized factories, mobility, and digital healthcare. The company employs around 24,000 people globally and reported revenues exceeding $9 billion in FY24, creating technologies that transform lives across various sectors.