4 months ago
Base Salary
$195k - $285k/yr
Responsibilities
- Develop, enhance, and maintain software kernels for next-generation AI hardware.
- Map algorithms and ML framework computational graphs to underlying hardware architectures.
- Optimize hardware-software co-design tradeoffs across the full-stack toolchain.
- Implement ML operators including GEMMs, convolutions, BLAS, softmax, layer normalization, pooling, and SIMD operations.
- Build scalable software deliverables within tight development windows.
- Collaborate with compiler, ML, systems, mixed-signal, DSP, and CPU experts to productize the software stack.
Requirements
- MS in computer engineering, math, physics, or a related field with 12+ years of industry experience, or a PhD in one of those fields with 7+ years of industry experience.
- Strong understanding of computer architecture, data structures, system software, and machine learning fundamentals.
- Proficiency in C/C++ and Python development in Linux environments using standard development tools.
- Experience implementing algorithms for FPGAs, DSPs, GPUs, AI accelerators, and embedded SIMD vector processors such as Tensilica.
- Experience with ML operators including GEMMs, convolutions, BLAS, softmax, layer normalization, and pooling.
- Preferred experience includes startup or small-team work, TensorFlow or PyTorch, ML compilers such as MLIR, LLVM, TVM, or Glow, and ML models for computer vision, NLP, or recommendation.
- Strong ownership, leadership, self-motivation, and teamwork skills.
Benefits
- Hybrid work arrangement with onsite work at the Santa Clara, California headquarters 3–5 days per week.
- Equal opportunity workplace and affirmative action employer.
About d-Matrix
d-Matrix builds AI inference computing platforms for data centers, combining custom silicon with systems, networking, and software. Its flagship Corsair platform and JetStream fabric focus on low-latency, energy-efficient generative AI inference at scale. Founded in 2019 and headquartered in Santa Clara, California, the privately held company sells hardware with accompanying software to cloud providers and enterprises deploying large AI models.