Principal Deep Learning Software Engineer, LLM Performance

at Nvidia
📍 Santa Clara, United States
USD 272,000-425,500 per year
SENIOR
✅ Hybrid

SCRAPED

Used Tools & Technologies

Not specified

Required Skills & Competences ?

Software Development @ 4 Python @ 4 TensorFlow @ 4 Hiring @ 4 Performance Optimization @ 4 Debugging @ 4 LLM @ 4 PyTorch @ 4 CUDA @ 4 GPU @ 4

Details

NVIDIA is seeking an experienced Deep Learning Software Engineer passionate about analyzing and improving the performance of Large Language Model (LLM) inference. This role focuses on performance optimization, deployment, and serving of deep learning solutions, with an emphasis on GPU-accelerated software such as TensorRT, benchmarking tools, and development for a wide range of NVIDIA accelerators.

Responsibilities

  • Optimize, analyze, and tune performance of LLM, Vision Language Models (VLM), and Generative AI models for inference, serving, and deployment within NVIDIA and open-source LLM frameworks.
  • Scale performance across various NVIDIA architectures from datacenter GPUs to edge SoCs, targeting max throughput, minimum latency, and constrained latency throughput.
  • Contribute code and features to TensorRT LLM, VLLM, SGLang, Triton, and inference benchmarking frameworks.
  • Collaborate with cross-functional teams across generative AI, automotive, image understanding, and speech understanding domains to develop innovative solutions.

Requirements

  • Bachelor’s, Master’s, or PhD in Computer Engineering, Computer Science, EECS, AI, or equivalent experience.
  • Minimum 12 years of relevant software development experience.
  • Expert programming skills in Python, C, and C++.
  • Experience with deep learning frameworks such as PyTorch, JAX, or TensorFlow.

Preferred Qualifications

  • Experience with LLM frameworks or deep learning compilers related to inference and deployment.
  • Background in performance modeling, profiling, debugging, and optimizing deep learning or high-performance computing applications.
  • Architectural knowledge of CPUs and GPUs.
  • GPU programming experience (CUDA or OpenCL).

Benefits

  • Competitive base salary range from $272,000 to $425,500 USD.
  • Eligibility for equity and benefits.
  • Hybrid work arrangement.

NVIDIA is an equal opportunity employer committed to diversity and inclusion in its hiring and promotion practices.