Full-Time

AI GPU Performance Engineer

Modular

Modular

51-200 employees

Unified platform for developing and deploying AI

AI & Machine Learning

$234000 - $319000

Annual target bonus, Equity

Mid

Remote in USA + 1 more

Required Skills
CUDA
Requirements
  • 3+ years of relevant experience working on complex code and systems.
  • Experience with GPU programming languages such as CUDA or OpenCL.
  • Experience with GPU assembly such as PTX and SASS.
  • Strong understanding of GPU architectures and performance optimizations.
  • Experience with AI workloads and performance tuning considerations such as fusion strategies;
  • Experience with core AI kernels such as matrix multiply and convolution.
  • Strong familiarity with using GPU profilers, debuggers, etc.
  • Deep interest in machine learning technologies and use cases.
Responsibilities
  • Design, develop, and optimize high-performance AI numeric and data manipulation kernels/operators for GPUs.
  • Achieve state-of-the-art performance by leveraging software and micro-architectural features of GPUs.
  • Work with compiler, framework, and runtime teams to deliver end-to-end performance that fully utilizes GPU workstations and servers.
  • Collaborate with machine learning researchers to guide system development for future ML trends.

Company Stage

Series A

Total Funding

$130M

Headquarters

,

Founded

2022

Growth & Insights
Headcount

6 month growth

8%

1 year growth

30%

2 year growth

633%