Principal Software Engineer - R&D at d-Matrix

Santa Clara, California, United States

Apply Now

$234,400 – $261,600Compensation

Senior (5 to 8 years), Expert & Leadership (9+ years)Experience Level

Full TimeJob Type

UnknownVisa

AI, TechnologyIndustries

Requirements

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
Experience tuning LLMs to generate code
Exposure to building software kernels for HW architectures
Understanding of domain-specific hardware architectures (e.g., GPUs, ML accelerators, SIMD vector processors, DSPs) and mapping ML algorithms (e.g., nonlinear operations, complex data manipulation) to accelerator architectures
Understanding of mapping computational graphs from AI frameworks (e.g., PyTorch, TensorFlow) to underlying architectures
Knowledge of evaluating throughput and latency performance for accelerators and modifying algorithms for numerical accuracy
Preferred
Prior startup, small team, or incubation experience
Experience designing and implementing algorithms for specialized hardware (e.g., FPGAs, DSPs, GPUs, AI accelerators) using libraries like CUDA
Experience with development for embedded SIMD vector processors (e.g., Tensilica)
Experience with ML frameworks such as TensorFlow and/or PyTorch
Experience with ML compilers and algorithms (e.g., MLIR, LLVM, TVM, Glow)
Work experience at a cloud provider or AI compute/subsystem company

Responsibilities

Be part of the team designing the SW stack for the AI compute engine
Lead the research and development of LLM-based kernel code generation for the software kernel SDK for next-generation AI hardware
Design and implement operations for large language and multimodal models (e.g., SIMD operations, matrix multiplications, convolution operations)
Integrate operations to build kernels such as LayerNorms, convolution layers, attention heads, or KV caches
Implement kernels using d-Matrix HW ISA and/or ISAs for third-party IP-based processor units

Skills

Key technologies and capabilities for this role

LLMCode GenerationKernel DevelopmentGPUML AcceleratorsSIMDDSPMatrix MultiplicationConvolutionLayerNormAttention HeadsKV CacheCompilerISA

Questions & Answers

Common questions about this position

What is the salary range for the Principal Software Engineer - R&D position?

The salary range is $234.4K - $261.6K.

Is this role remote or hybrid, and what's the location policy?

This is a hybrid role requiring onsite work at the Santa Clara, CA headquarters 3-5 days per week.

What key skills and experience are required for this role?

Required skills include experience tuning LLMs to generate code, building software kernels for HW architectures, understanding domain-specific hardware like GPUs and ML accelerators, mapping ML algorithms to accelerators, and proficiency in C/C++ and Python in Linux. A MS or PhD in Computer Science, Electrical Engineering, or related fields is minimum, along with experience as a technical R&D lead and in designing/fine-tuning generative AI LLMs for code generation.

What is the company culture like at d-Matrix?

The culture emphasizes respect and collaboration, valuing humility, direct communication, inclusivity, and diverse perspectives for better solutions. They seek passionate individuals driven by execution to tackle challenges in AI innovation.

What makes a strong candidate for this Principal Software Engineer role?

Strong candidates have a MS or PhD, experience leading technical R&D for AI accelerator software, a track record in fine-tuning LLMs for code generation with open-source contributions or publications, and hands-on expertise in kernel development for AI hardware.

d-Matrix

AI compute platform for datacenters

About d-Matrix

d-Matrix focuses on improving the efficiency of AI computing for large datacenter customers. Its main product is the digital in-memory compute (DIMC) engine, which combines computing capabilities directly within programmable memory. This design helps reduce power consumption and enhances data processing speed while ensuring accuracy. d-Matrix differentiates itself from competitors by offering a modular and scalable approach, utilizing low-power chiplets that can be tailored for different applications. The company's goal is to provide high-performance, energy-efficient AI inference solutions to large-scale datacenter operators.

Santa Clara, CaliforniaHeadquarters

2019Year Founded

$149.8MTotal Funding

SERIES_BCompany Stage

Enterprise Software, AI & Machine LearningIndustries

201-500Employees