Overview
In this role you will design, bring up, and optimize DSP and AI workloads on Arm-based platforms. You’ll work closely with hardware architects and software teams to enable platforms, port operating systems, and demonstrate performance of Arm solutions. You’ll tackle low-level embedded development, processor architecture awareness, and system-level integration to deliver scalable, high-performance workloads. Join a collaborative team shaping future Arm technologies through hands-on optimization and demonstrations.
Responsibilities
- Platform bring-up across bare-metal, RTOS, Zephyr and embedded Linux
- Performance optimization of DSP, audio, vision and AI workloads using Arm features (MVE, NEON, SVE2, SME)
- Develop and optimize compute libraries and kernels (FFT, filters, image processing, ML preprocessing)
- System integration of sensors, memory subsystems, DMA, accelerators, and software components
- Benchmarking and profiling using hardware counters and profiling tools
- Technical demonstrations of Arm processors and accelerators
- Collaboration with processor architects, software teams, and silicon partners to identify bottlenecks and propose improvements
Key requirements
- Strong proficiency in C/C++ and low-level embedded programming
- Solid understanding of processor architectures, memory hierarchies, caches, DMA, and interrupt handling
- Familiarity with RTOS, Zephyr, or Linux
- Experience with performance profiling and code optimization
- Familiarity with DSP algorithms, fixed-point arithmetic, and SIMD/vector processing
- Experience with embedded development tools, compilers, debuggers, and hardware evaluation boards
- Strong problem-solving abilities and collaborative mindset
- Strong communication skills
- collaboration
- problem-solving
- communication
- Arm Cortex-M and Cortex-A architectures
- MVE (Helium), NEON, SVE2, or assembly-level optimization
- CMSIS-DSP, CMSIS-NN, or equivalent compute libraries
…
