Job description
At d-Matrix, we are focused on unleashing the potential of generative AI to power the transformation of technology. We are at the forefront of software and hardware innovation, pushing the boundaries of what is possible. Our culture is one of respect and collaboration.
We value humility and believe in direct communication. Our team is inclusive, and our differing perspectives allow for better solutions. We are seeking individuals passionate about tackling challenges and are driven by execution. Ready to come find your playground? Together, we can help shape the endless possibilities of AI.
Location:
Hybrid, working onsite at our Santa Clara, CA, headquarters 3-5 days per week.
The Role: Principal Software Engineer - R&D
What you will do:
The principal engineer role requires you to be part of the team that helps design the SW stack for our AI compute engine. As part of the software team, you will lead the research and development of LLM-based kernel code generation for the software kernel SDK for next-generation AI hardware. The d-Matrix software stack is a hybrid software stack that utilizes a compiler as well as kernels. The kernels team designs and implements operations for large language and multimodal models, such as SIMD operations, matrix multiplications, and convolution operations, and integrates these operations to build kernels such as LayerNorms, convolution layers, attention heads, or KV caches. These kernels are implemented in a combination of the d-Matrix HW ISA and/or ISAs for third-party IP-based processor units.
What you will bring:
Experience tuning LLMs to generate code. You have exposure to building software kernels for HW architectures. You possess an understanding of domain-specific hardware architectures (for example, GPUs, ML accelerators, SIMD vector processors, and DSPs) and how to map ML algorithms, such as nonlinear operations or complex data manipulation operations, to an accelerator architecture. You understand how to map computational graphs generated by AI frameworks (such as PyTorch or TensorFlow) to an underlying architecture. You also understand how to evaluate throughput and latency performance for such accelerators, as well as how to modify the algorithms for numerical accuracy. Your role will be to research and develop ways of generating kernel code through LLMs.
Minimum:
MS or PhD in Computer Science, Electrical Engineering, or related fields
Strong grasp of computer architecture, data structures, system software, and machine learning fundamentals
Experience as technical R&D lead, manager, or senior manager level with software for AI accelerator HW and models for code generation
Experience in designing and fine-tuning generative AI LLM models for code generation and/or coding assistance with a record of open-source code and/or publications in this field.
Proficient in C/C++ and Python development in Linux environment and using standard development tools
Self-motivated team player with a strong sense of ownership and leadership
Preferred:
Prior startup, small team, or incubation experience
Experience design and implementing algorithms for specialized hardware such as FPGAs, DSPs, GPUs, AI accelerators using libraries such as CUDA, etc.
Experience with development for embedded SIMD vector processors such as Tensilica
Experience with ML frameworks such as TensorFlow and/or PyTorch
Experience working with ML compilers and algorithms, such as MLIR, LLVM, TVM, Glow, etc.
Work experience at a cloud provider or AI compute/subsystem company
Equal Opportunity Employment Policy
d-Matrix is proud to be an equal opportunity workplace and affirmative action employer. We’re committed to fostering an inclusive environment where everyone feels welcomed and empowered to do their best work. We hire the best talent for our teams, regardless of race, religion, color, age, disability, sex, gender identity, sexual orientation, ancestry, genetic information, marital status, national origin, political affiliation, or veteran status. Our focus is on hiring teammates with humble expertise, kindness, dedication and a willingness to embrace challenges and learn together every day.
d-Matrix does not accept resumes or candidate submissions from external agencies. We appreciate the interest and effort of recruitment firms, but we kindly request that individual interested in opportunities with d-Matrix apply directly through our official channels. This approach allows us to streamline our hiring processes and maintain a consistent and fair evaluation of al applicants. Thank you for your understanding and cooperation.
