Manager, Large Language Model Inference

NVIDIA

Multiple Locations
Base: 184,000 usd - 287,500 usd for level 2; 224,0...
Hybrid
C++ or python expertise
Experience with llms and vlms
Technical leadership experience
NVIDIA is accelerating the AI revolution with its TensorRT inference platform

Job Summary

  • NVIDIA is accelerating the AI revolution with its TensorRT inference platform.
  • The role involves leading a team to develop LLM/VLM/VLA inference software technologies.
  • Candidates will work collaboratively with researchers and architects to deliver high-performance AI software.

Matching Summary

NVIDIA is accelerating the AI revolution with its TensorRT inference platform.

Salary

Base: 184,000 USD - 287,500 USD for Level 2; 224,000 USD - 356,500 USD for Level 3; Benefits: Not specified

Skills & Requirements

Must-have

  • C++ or Python expertise
  • Experience with LLMs and VLMs
  • Technical leadership experience

Nice-to-have

  • Understanding of GPU architecture
  • Passion for user-friendly APIs
  • Experience with TensorRT-LLM

Key Requirements

  • MS, PhD, or equivalent experience
  • 7+ years of software engineering experience
  • 3+ years of technical leadership experience

Work Rights

Not specified

Tailored Resume

Cover Letter