Developer – AI Embedded Toolchains page is loaded
Developer – AI Embedded Toolchains
Location: Cork-Ireland, Limerick-Ireland, Edinburgh – UK
About Analog Devices
Analog Devices (ADI) is a global leader in high-performance analog, mixed-signal, and digital signal processing (DSP) technologies. Our AI/ML initiatives focus on delivering cutting-edge solutions that empower embedded developers to seamlessly integrate AI into their applications.
About the Role
We are looking for a Developer – AI Embedded Toolchains to contribute to the development of a state-of-the-art toolchain for compiling, optimizing, and deploying AI models to ADI’s embedded hardware platforms, including those with advanced DSPs and NPUs. This role will involve working with existing AI toolchains such as Cadence NeuroWeave SDK, Arm Vela, and others while helping to create a best-in-class development experience.
The ideal candidate has strong experience in embedded development, compiler toolchains, and cross-compilation. Familiarity with AI toolchains, model optimization, and inference engines is a plus but not required.
Key Responsibilities
* Develop and enhance AI toolchains for ADI’s embedded platforms.
* Integrate and improve compiler workflows, including cross-compilation and optimization for DSPs and NPUs.
* Extend and adapt existing AI toolchains such as Cadence NeuroWeave SDK, Arm Vela, and others.
* Optimize AI inference performance by improving memory efficiency, execution speed, and hardware utilization.
* Work closely with internal teams, including hardware architects, compiler engineers, and AI researchers, to refine toolchain capabilities.
* Implement debugging, profiling, and visualization tools to support embedded AI development.
* Stay up to date with trends in embedded AI, compiler technologies, and model deployment techniques.
Required Qualifications
* 5+ years of experience with embedded development, including cross-compilers, linker scripts, and low-level system optimizations.
* Proficiency in C/C++ and Python for toolchain and compiler development.
* Familiarity with compiler toolchains, such as LLVM, GCC, or proprietary backends.
* Understanding of DSPs and NPUs, including hardware acceleration techniques.
* Basic familiarity with AI toolchains (e.g., model conversion, quantization, inference runtime optimizations).
* Understanding of AI frameworks (TensorFlow, PyTorch, ONNX) and their deployment workflows.
* Strong problem-solving and debugging skills for embedded systems.
Preferred Qualifications
* Experience working with Cadence NeuroWeave SDK, Arm Vela, or similar AI toolchains.
* Familiarity with inference engines such as TensorFlow Lite Micro (TFLM), ONNX Runtime, or similar.
* Knowledge of model optimization techniques such as quantization, pruning, and graph optimizations.
* Experience with AI deployment on embedded platforms in automotive, industrial, or IoT applications.
* Contributions to open-source AI compilers (TVM, Glow, MLIR) or inference runtimes.
* Experience working with RTOS and real-time AI constraints.
Why Join Us?
* Work on cutting-edge AI acceleration for embedded systems.
* Collaborate with top-tier hardware and AI engineers in a fast-growing AI division.
* Drive real-world AI deployments on power-efficient, high-performance ADI platforms.
* Competitive compensation, benefits, and opportunities for career growth.
If you’re excited about developing next-generation AI toolchains for embedded systems, we’d love to hear from you!
#J-18808-Ljbffr