Ai Inference Performance Engineer

Topjobstoday

Base: 152,000 usd - 241,500 usd; bonus/equity: not...
**
5+ years software development experience
Strong python or c++ programming skills
Expertise with dl frameworks like pytorch
** The position of AI Inference Performance Engineer at Topjobstoday involves optimizing and benchmarking GenAI inference on NVIDIA accelerators, focusing on performance standards across various AI workloads. The role requires extensive experience in software development, particularly with deep learning frameworks, as well as strong technical leadership and collaboration skills. **

Job Summary

  • This role involves optimizing and benchmarking GenAI inference on NVIDIA's latest accelerators.
  • You will collaborate with various teams to push performance on large-scale models and workloads.
  • Join a team that values technical leadership and innovation in AI computing.

Matching Summary

Match Score: 75

** The position of AI Inference Performance Engineer at Topjobstoday involves optimizing and benchmarking GenAI inference on NVIDIA accelerators, focusing on performance standards across various AI workloads. The role requires extensive experience in software development, particularly with deep learning frameworks, as well as strong technical leadership and collaboration skills. **

Salary

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

Skills & Requirements

Must-have

  • 5+ years software development experience
  • Strong Python or C++ programming skills
  • Expertise with DL frameworks like PyTorch

Nice-to-have

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

Key Requirements

  • BS, MS, or PhD in relevant fields
  • Proven track record in deep learning inference
  • Deep understanding of LLM/VLM architectures

Work Rights

Not specified

Tailored Resume

Cover Letter