Ai Inference Performance Engineer

NVIDIA

Base: 152,000 usd - 241,500 usd; bonus/equity: not...
Hybrid
Strong python or c++ programming skills
Expertise with a dl framework
Proven track record in deep learning inference
This role involves driving industry benchmark results and optimizing the end-to-end optimization pipeline

Job Summary

  • This role involves driving industry benchmark results and optimizing the end-to-end optimization pipeline.
  • You will collaborate with framework and kernel teams to enhance performance on large-scale models.
  • NVIDIA is committed to fostering a diverse work environment and values equal opportunity.

Matching Summary

This role involves driving industry benchmark results and optimizing the end-to-end optimization pipeline.

Salary

Base: 152,000 USD - 241,500 USD; Bonus/Equity: Not specified; Benefits: Not specified

Skills & Requirements

Must-have

  • Strong Python or C++ programming skills
  • Expertise with a DL framework
  • Proven track record in deep learning inference

Nice-to-have

  • Experience with performance modeling
  • Knowledge of GPU programming
  • Track record of leading technical programs

Key Requirements

  • BS, MS, or PhD in relevant fields
  • 5+ years of relevant software development experience
  • Deep understanding of LLM/VLM architectures

Work Rights

Not specified

Tailored Resume

Cover Letter