Deep Learning Software Engineer, Llm Performance - New College Grad 2026

NVIDIA

Base: 124,000 usd - 195,500 usd (level 2); 152,000...
Hybrid
Llm inference performance analysis
Gpu-accelerated deep learning software
Tensorrt llm, vllm, sglang implementation
NVIDIA is seeking experienced Deep Learning Engineers passionate about analyzing and improving the performance of LLM inference, contributing to the revolution in deep learning powered by NVIDIA GPUs

Job Summary

  • NVIDIA is seeking experienced Deep Learning Engineers passionate about analyzing and improving the performance of LLM inference, contributing to the revolution in deep learning powered by NVIDIA GPUs.
  • The role involves performance optimization, analysis, and tuning of LLM, VLM and GenAI models for DL inference, serving and deployment in NVIDIA/OSS LLM frameworks across different NVIDIA accelerators.
  • You will collaborate with diverse teams and contribute features and code to NVIDIA/OSS LLM frameworks, inference benchmarking frameworks, TensorRT, and Triton to develop innovative solutions.

Matching Summary

NVIDIA is seeking experienced Deep Learning Engineers passionate about analyzing and improving the performance of LLM inference, contributing to the revolution in deep learning powered by NVIDIA GPUs.

Salary

Base: 124,000 USD - 195,500 USD (Level 2); 152,000 USD - 241,500 USD (Level 3); Equity and benefits eligible

Skills & Requirements

Must-have

  • LLM inference performance analysis
  • GPU-accelerated deep learning software
  • TensorRT LLM, VLLM, SGLang implementation
  • Python/C/C++ programming skills
  • Deep learning framework experience

Nice-to-have

  • Performance modeling and profiling
  • Architectural knowledge of CPU and GPU
  • Cross-collaborative team work
  • Generative AI, automotive, image understanding, speech understanding

Key Requirements

  • Bachelors, Masters, PhD, or equivalent experience
  • 2+ years of relevant software development experience
  • Experience with DL framework like PyTorch, JAX, TensorFlow
  • Prior experience with LLM framework or DL compiler
  • GPU programming experience (CUDA or OpenCL)

Work Rights

Not specified

Tailored Resume

Cover Letter