Member of Technical Staff - ML Performance
Member of Technical Staff - ML Performance
Member of Technical Staff - ML Performance
Modal
Modal is a fast-growing AI infrastructure company providing GPU access and container solutions for AI teams. They are seeking experienced engineers to enhance the performance of ML systems, particularly in relation to language and diffusion models.
Qualification
- 5+ years of experience writing high-quality, high-performance code.
- Experience with torch and high-level ML frameworks.
- Familiarity with Nvidia GPU architecture and CUDA.
- Experience with ML performance engineering and inference engines like vLLM or TensorRT.
- Nice-to-have: familiarity with low-level operating system foundations such as Linux kernel and containers.
Responsibility
- Contribute to open-source projects related to ML performance engineering.
- Enhance Modal's container runtime for improved model throughput and latency.
- Collaborate with the engineering team to optimize ML systems at scale.
- Debug and resolve performance issues related to GPU utilization.
- Implement high-performance algorithms for machine learning applications.
