GenAI Performance Engineer
GenAI Performance Engineer
modularai
Modular is seeking a GenAI Performance Engineer to enhance the performance of their MAX product, which aims to simplify AI development and deployment. The role involves collaboration with various engineering teams to optimize performance across different hardware configurations, contributing to the next generation AI platform.
Qualification
- Experience in performance engineering or optimization, particularly in AI or machine learning contexts
- Strong understanding of AI models and their deployment challenges
- Familiarity with performance analysis tools and methodologies
- Experience working with CPU, GPU, and Accelerator hardware
- Ability to collaborate effectively with cross-functional teams
Responsibility
- Measure, analyze, and identify opportunities to improve the performance of the MAX product under realistic and relevant usage patterns
- Partner with the product and customer teams to understand the performance of the MAX product in both standard and cutting-edge AI applications and design benchmarks to reflect them
- Collaborate with the kernels and GenAI modeling team to bring up new model families
- Build and apply performance analysis tooling to study and optimize the performance of MAX Engine and MAX Serve
- Conduct deep dives on high-value models to push Modular’s performance further
