Responsibilities
- Develop, enhance, and maintain software kernels for next-generation AI hardware.
- Productize the software stack for the company’s AI compute engine.
- Map algorithms and computational graphs generated by AI frameworks to underlying hardware architectures.
- Optimize and balance hardware-software co-design tradeoffs across the full-stack toolchain.
- Build and scale software deliverables within tight development windows.
- Collaborate with compiler experts on compiler infrastructure and with ML, systems, mixed-signal, DSP, and CPU hardware experts.
Requirements
- A master’s degree in computer engineering, math, physics, or a related field with 5+ years of industry experience, or a PhD in one of these fields with 1+ 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 specialized hardware including FPGAs, DSPs, GPUs, and AI accelerators using libraries such as CUDA.
- Experience implementing ML operators including GEMMs, convolutions, BLAS, and SIMD operators for softmax, layer normalization, and pooling.
- Experience developing for embedded SIMD vector processors such as Tensilica.
- Experience with ML frameworks such as TensorFlow or PyTorch is preferred.
- Experience with ML compilers and algorithms such as MLIR, LLVM, TVM, or Glow is preferred.
- Experience with deep-learning frameworks and models for computer vision, NLP, or recommendation is preferred.
- Prior startup, small-team, incubation, cloud-provider, or AI compute/subsystem company experience is preferred.
Benefits
- Hybrid role working onsite at the Bangalore, India, offices 3–5 days per week.
About d-Matrix
d-Matrix is an AI infrastructure company building the next generation of inference computing for the era of generative and agentic AI. Founded in 2019, d-Matrix is rethinking AI inference from the ground up with a full-stack approach spanning silicon, systems, networking, and software. Its flagship products, including the Corsair™ inference platform and JetStream™ inference fabric, are purpose-built to deliver high-performance, low-latency, and energy-efficient AI inference at datacenter scale. The company has raised nearly $500 million from a global syndicate of leading venture capital firms, sovereign wealth funds, and strategic investors, including Playground Global, Bullhound Capital, M12 (Microsoft’s Venture Fund), SK hynix, Temasek, Qatar Investment Authority, and Singapore’s EDBI. The company’s most recent financing valued d-Matrix at approximately $2 billion. As AI shifts from training to inference, the demands on AI infrastructure are changing. d-Matrix is building the infrastructure required to power the next generation of real-time AI at scale.