Senior Software Engineer - Kernels

Job Title

Senior Software Engineer - Kernels

Role Summary

Develop, optimize, and maintain software kernels and related toolchain to productize the software stack for a next-generation AI compute engine. Collaborate with compiler, ML, systems and hardware teams to map computational graphs and algorithms to the underlying hardware and drive hardware–software co-design decisions.

Hybrid role based in the Belgrade office (3–5 days per week).

Experience Level

Senior — typical background: MS +5 years industry experience or PhD +1 year. Requires significant experience with kernel development for specialized hardware and hardware–software co-design.

Responsibilities

Core responsibilities for this role include development, optimization, and cross-team collaboration focused on software kernels for AI hardware.

• Design, develop, enhance, and maintain software kernels for AI accelerators and related HW architectures.
• Map algorithms and computational graphs from ML frameworks to target hardware, ensuring correctness and performance.
• Optimize operators commonly used in ML workloads (GEMM, convolutions, BLAS, SIMD ops such as softmax, layer normalization, pooling).
• Work across the full-stack toolchain and collaborate with compiler experts to build compiler infrastructure and runtime components.
• Make engineering trade-offs for hardware–software co-design and optimize for performance, area, and power where relevant.
• Deliver scalable software deliverables within tight development timelines and participate in code and design reviews.

Requirements

Must-have technical skills and practical experience.

• Strong understanding of computer architecture, data structures, system software, and machine learning fundamentals.
• Proficient in C/C++ and Python development on Linux using standard development tools and workflows.
• Experience implementing algorithms and ML operators in high-level languages (C/C++, Python).
• Experience developing for specialized hardware (FPGAs, DSPs, GPUs, AI accelerators) and using libraries such as CUDA.
• Experience with embedded SIMD/vector processors (example: Tensilica) and SIMD programming techniques.
• Practical experience mapping computational graphs from ML frameworks to hardware and working across the full toolchain.
• Self-motivated, strong ownership, good communicator, and effective collaborator in cross-functional teams.

Nice-to-have:

• Prior startup, small-team, or incubation experience.
• Experience with ML frameworks such as TensorFlow and/or PyTorch.
• Experience with ML compilers and tools (MLIR, LLVM, TVM, Glow, etc.).
• Experience with deep learning models for CV, NLP, or recommendation systems.
• Work experience at a cloud provider or AI compute/subsystem company.

Education Requirements

MS in computer engineering, mathematics, physics, or a related technical field with 5+ years of industry experience; or PhD in computer engineering, mathematics, physics, or a related technical field with 1+ years of industry experience.

About the Company

Company: d-Matrix

Headquarters: Santa Clara, California, United States

d-Matrix is a Santa Clara–based startup developing highly programmable in-memory computing architectures and accompanying software to accelerate generative AI and other AI workloads, focusing on hardware-software co-design for cloud and edge applications.