Internship

AI / ML Software Engineer – Intern

Posted on 6/10/2024

d-Matrix

d-Matrix

51-200 employees

AI compute platform using in-memory computing

AI & Machine Learning
Data & Analytics
Hardware

Santa Clara, CA, USA

Required Skills
Python
Tensorflow
Pytorch
Quality Assurance (QA)
REST APIs
Requirements
  • Enrolled in a Bachelor's degree in Computer Science, Electrical and Computer Engineering, or a related scientific discipline.
  • Proficient in programming with either Python/C/C++ programming languages.
  • Enrolled in either a MS or PhD in Computer Science, Electrical and Computer Engineering, or a related scientific discipline.
  • Understanding of CPU / GPU architectures and their memory systems.
  • Experience with specialized HW accelerators for deep neural networks.
  • Experience developing high performance kernels, simulators, debuggers, etc. targeting GPUs/Other accelerators.
  • Experience using Machine Learning frameworks, like PyTorch (preferrable), Tensorflow, etc.
  • Experience with Machine Learning compilers, like MLIR (preferrable), TVM etc.
  • Experience deploying inference pipelines.
  • Experience using or developing inference engines such as vLLM, TensorRT-LLM.
  • Passionate about AI and thriving in a fast-paced and dynamic startup culture.
Responsibilities
  • Develop performant implementations of SOTA ML models such as LLaMA, GPT, BERT, DLRM, etc.
  • Develop and maintain tools for performance simulation, analysis, debugging, profiling.
  • Develop AI infra software such as kernel compiler, inference engine, model factory, etc.
  • Develop QA systems/automation software.
  • Engage and collaborate with the rest of the SW team to meet development milestones.
  • Contribute to publication of papers and intellectual properties as applicable.

d-Matrix is developing a unique AI compute platform using in-memory computing (IMC) techniques with chiplet level scale-out interconnects, revolutionizing datacenter AI inferencing. Their innovative circuit techniques, ML tools, software, and algorithms have successfully addressed the memory-compute integration problem, enhancing AI compute efficiency.

Company Stage

Series B

Total Funding

$161.5M

Headquarters

Santa Clara, California

Founded

2019

Growth & Insights
Headcount

6 month growth

0%

1 year growth

28%

2 year growth

203%
INACTIVE