Embedded AI Tools Engineer

Analog Devices•Wilmington, MA

23h•Onsite

About The Position

Analog Devices is seeking an Embedded AI Tools Engineer to join their Embedded AI Tooling Team. This role involves developing next-generation embedded AI deployment infrastructure and model optimization tools for cutting-edge SoCs. The engineer will be instrumental in designing and implementing technology that will transform the semiconductor industry, enabling system engineers and research scientists to deliver AI-based solutions using ADI hardware. Key responsibilities include designing, testing, implementing, and releasing AI model deployment tools and infrastructure for heterogeneous computer architectures, building end-to-end workflows for model development and deployment, developing tools for hardware-aware model design, designing model compilation and optimization pipelines, and exploring agentic AI workflows for automated model-hardware co-optimization.

Requirements

Strong embedded systems and computer architecture experience (bare-metal, RTOS, or embedded Linux).
Expertise in end-to-end AI/ML model development, from training through optimization and deployment on embedded platforms.
Experience with hardware-aware neural architecture design and model optimization techniques tailored to specific processor architectures.
Proficiency in C, C++, Python, with experience in firmware and low-level software development.
Deep understanding of neural network quantization, pruning, knowledge distillation, and optimization techniques for resource-constrained devices.
Knowledge of neural network accelerators (NPUs, DSPs) and efficient execution of neural networks on heterogeneous hardware.
Familiarity with AI/ML frameworks (TensorFlow, PyTorch) and deployment tools (TensorFlow Lite, ONNX Runtime, TVM, etc.).
Experience with build systems (CMake, Make, Ninja), CI/CD pipelines, and infrastructure automation.
Background in ML algorithms (CNN, DNN, Transformer architectures) and their embedded implementation.
Familiarity with developer tooling (debuggers, profilers, SDKs, system configuration tools).

Nice To Haves

Experience with hardware-software co-design and custom operator development for specialized hardware.
Knowledge of neural architecture search (NAS) and automated model optimization techniques.
Background in digital signal processing (DSP) and algorithm implementation experience.
Experience with edge AI frameworks and deployment tools (TensorFlow Lite Micro, ONNX, Apache TVM, MLIR).
Understanding of compiler optimizations and code generation for embedded AI accelerators.
Experience with FPGA development including design, synthesis, simulation, and verification.
Experience with Zephyr RTOS and open-source RTOS ecosystems.
Experience contributing to and working with open-source ecosystems.
Understanding of heterogeneous architectures (ARM, RISC-V, DSPs, custom SoCs).

Responsibilities

Design, test, implement, and release novel AI model deployment tools and infrastructure for heterogeneous computer architectures (DSPs, NPUs, CPUs) as part of a larger SoC.
Build end-to-end workflows spanning model development, optimization, hardware-specific architecture, and deployment to ADI's embedded platforms.
Develop tools and infrastructure for hardware-aware model design, including architecture mapping techniques.
Design and implement model compilation and optimization pipelines for seamless quantization, pruning, layer fusion, and hardware-specific code generation.
Explore and prototype agentic AI workflows for automated model-hardware co-optimization, intelligent architecture search, and adaptive deployment strategies.