Product Manager, Ai Platform Kernels And Communication Libraries

NVIDIA

Base: 168,000 usd - 258,750 usd (level 4); 208,000...
Gpu acceleration developer products
Cuda execution models
Multi-gpu protocols
Architect developer-focused products that simplify high-performance inference and training deployment across diverse GPU architectures

Job Summary

  • Architect developer-focused products that simplify high-performance inference and training deployment across diverse GPU architectures.
  • Define the multi-year strategy for kernel and communication libraries by analyzing performance bottlenecks in emerging AI workloads.
  • Partner with open-source communities like Triton and FlashInfer to shape and drive ecosystem-wide roadmaps.

Matching Summary

Architect developer-focused products that simplify high-performance inference and training deployment across diverse GPU architectures.

Salary

Base: 168,000 USD - 258,750 USD (Level 4); 208,000 USD - 327,750 USD (Level 5); Bonus/Equity: Equity eligible; Benefits: Benefits eligible

Skills & Requirements

Must-have

  • GPU acceleration developer products
  • CUDA execution models
  • multi-GPU protocols
  • HPC optimization stacks
  • low-level GPU programming
  • developer enablement

Nice-to-have

  • cost-per-inference models
  • energy efficiency
  • cluster scaling factors
  • open-source community engagement

Key Requirements

  • 7+ years technical PM experience
  • BS or MS or equivalent experience
  • Expert-level understanding of CUDA
  • Proven track record translating hardware to software roadmaps

Work Rights

Not specified

Tailored Resume

Cover Letter