Senior Dl Algorithms Engineer - Inference Performance

NVIDIA

Base: $184,000 - $287,500 (level 4) or $224,000 - ...
5+ years of experience in deep learning
Proficient in c++ and pytorch frameworks
Strong background in gpu architecture fundamentals
This role involves implementing language and multimodal model inference as part of NVIDIA Inference Microservices

Job Summary

  • This role involves implementing language and multimodal model inference as part of NVIDIA Inference Microservices.
  • Candidates will profile and analyze bottlenecks across the full inference stack to push the boundaries of performance.
  • The position offers a competitive base salary ranging from $184,000 to $356,500 depending on the level, along with equity and benefits.

Matching Summary

This role involves implementing language and multimodal model inference as part of NVIDIA Inference Microservices.

Salary

Base: $184,000 - $287,500 (Level 4) or $224,000 - $356,500 (Level 5); Bonus/Equity: Eligible for equity; Benefits: Comprehensive benefits package included

Skills & Requirements

Must-have

  • 5+ years of experience in deep learning
  • Proficient in C++ and PyTorch frameworks
  • Strong background in GPU architecture fundamentals

Nice-to-have

  • Experience with CUDA or OpenCL programming
  • Deep understanding of modern LLM architectures
  • Proven system-level performance optimization skills

Key Requirements

  • PhD in CS, EE, CSEE or equivalent experience
  • Minimum 5 years of professional experience
  • Advanced proficiency in C++ and Deep Learning frameworks

Work Rights

Not specified

Tailored Resume

Cover Letter