Full-Time

Software Engineer – Senior Staff

Kernels

Confirmed live in the last 24 hours

d-Matrix

d-Matrix

51-200 employees

AI compute platform for datacenters

Hardware
Enterprise Software
AI & Machine Learning

Senior

Santa Clara, CA, USA

Hybrid position requiring onsite presence in Santa Clara, CA for 3 days per week.

Category
Backend Engineering
FinTech Engineering
Software Engineering
Required Skills
Python
CUDA
Data Structures & Algorithms
C/C++
FPGA
Linux/Unix
Requirements
  • MS or PhD in Computer Engineering, Math, Physics or related degree with 5+ years of industry experience.
  • Strong grasp of computer architecture, data structures, system software, and machine learning fundamentals.
  • Proficient in C/C++ and Python development in Linux environment and using standard development tools.
  • Experience implementing algorithms in high-level languages such as C/C++ and Python.
  • Experience implementing algorithms for specialized hardware such as FPGAs, DSPs, GPUs, and AI accelerators using libraries such as CuDA, etc.
  • Experience in implementing operators commonly used in ML workloads - GEMMs, Convolutions, BLAS, SIMD operators for operations like softmax, layer normalization, pooling, etc.
  • Experience with development for embedded SIMD vector processors such as Tensilica.
  • Self-motivated team player with a strong sense of ownership and leadership.
Responsibilities
  • You will be responsible for the development, enhancement, and maintenance of software kernels for next-generation AI hardware.
  • You possess experience building software kernels for HW architectures.
  • You possess a very strong understanding of various hardware architectures and how to map algorithms to the architecture.
  • You understand how to map computational graphs generated by AI frameworks to the underlying architecture.
  • You have had past experience working across all aspects of the full stack toolchain and understand the nuances of what it takes to optimize and trade-off various aspects of hardware-software co-design.
  • You can build and scale software deliverables in a tight development window.
  • You will work with a team of compiler experts to build out the compiler infrastructure, working closely with other software (ML, Systems) and hardware (mixed signal, DSP, CPU) experts in the company.

d-Matrix focuses on improving the efficiency of AI computing for large datacenter customers. The 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. Unlike many competitors, d-Matrix offers a modular and scalable approach, utilizing low-power chiplets that can be tailored for different applications. The goal is to provide high-performance AI inference solutions that are energy-efficient, catering specifically to the needs of large-scale datacenter operators.

Company Stage

Series B

Total Funding

$149.8M

Headquarters

Santa Clara, California

Founded

2019

Growth & Insights
Headcount

6 month growth

-14%

1 year growth

-3%

2 year growth

219%
Simplify Jobs

Simplify's Take

What believers are saying

  • Securing $110 million in Series B funding positions d-Matrix for rapid growth and technological advancements.
  • Their Jayhawk II silicon aims to solve critical issues in AI inference, such as cost, latency, and throughput, making generative AI more commercially viable.
  • The company's focus on efficient AI inference could attract significant interest from data centers and enterprises looking to deploy large language models.

What critics are saying

  • Competing against industry giants like Nvidia poses a significant challenge in terms of market penetration and customer acquisition.
  • The high dependency on continuous innovation and technological advancements could strain resources and lead to potential setbacks.

What makes d-Matrix unique

  • d-Matrix focuses on developing AI hardware specifically optimized for Transformer models, unlike general-purpose AI chip providers like Nvidia.
  • Their digital in-memory compute (DIMC) architecture with chiplet interconnect is a first-of-its-kind innovation, setting them apart in the AI hardware market.
  • Backed by major investors like Microsoft, d-Matrix has the financial support to challenge established players like Nvidia.

Help us improve and share your feedback! Did you find this helpful?