NVIDIA

Manager, Large Language Model Inference

NVIDIA(1 month ago)

HybridFull TimeManager$184,000 - $356,500Engineering
Apply Now

About this role

A hands-on Engineering Manager at NVIDIA leading the development of next-generation LLM/VLM inference software for the TensorRT platform. The role combines technical ownership and people leadership to architect and ship production-grade inference runtimes across enterprise and edge GPUs. It involves close collaboration with researchers, GPU architects, and cross-functional teams to accelerate AI deployment and performance.

View Original Listing

Required Skills

  • Kernel Development
  • Runtime Optimization
  • C++
  • Python
  • CUDA
  • GPU Architecture
  • Performance Tuning
  • LLM Inference
  • API Design
  • Team Leadership

+1 more

Qualifications

  • MS in Computer Science, Computer Engineering, AI or related field
  • PhD in Computer Science, Computer Engineering, AI or related field
  • Equivalent Experience
NVIDIA

About NVIDIA

nvidia.com

NVIDIA invents the GPU and drives advances in AI, HPC, gaming, creative design, autonomous vehicles, and robotics.

View more jobs at NVIDIA

ApplyBlast uses AI to match you with the right jobs, tailor your resume and cover letter, and apply automatically so you can land your dream job faster.

© All Rights Reserved. ApplyBlast.com