Head of GPU-Accelerated AI Inference

NVIDIA; Washington (District of Columbia); On-site; USD 224,000 - 431,250; Full time

Benefits offered by this job

Equity

Benefits package

Job summary

NVIDIA is seeking an exceptional Manager, Deep Learning Inference Software, to lead a world-class engineering team focused on deploying AI models with NVIDIA GPUs. The role shapes software powering large language models, multimodal, and generative AI, including open-source frameworks like SGLang, vLLM, and FlashInfer.

You will guide strategy, roadmaps, and end-to-end optimized inference pipelines across accelerators, while mentoring engineers and driving innovation in CUDA, Triton, and multi-GPU

Qualifications

• MS, PhD, or equivalent experience in Computer Science, Electrical/Computer Engineering, or related field.
• 6+ years of software development experience, including 3+ years in technical leadership or engineering management.
• Strong background in C/C++ software design and development; proficiency in Python is a plus.
• Hands-on experience with GPU programming (CUDA, Triton, CUTLASS) and performance optimization.
• Proven record of deploying or optimizing deep learning models in production environments.
• Experience leading teams using Agile or collaborative software development practices.

Responsibilities

• Lead, mentor, and scale a high-performing engineering team focused on deep learning inference and GPU-accelerated software.
• Guide the strategy, roadmap, and execution of NVIDIA's OSS inference frameworks engineering.
• Partner with internal compiler, libraries, and research teams to deliver end-to-end optimized inference pipelines across NVIDIA accelerators.
• Oversee performance tuning, profiling, and optimization of large-scale models for LLM, multimodal, and generative AI applications.
• Guide engineers in adopting best practices for CUDA, Triton, CUTLASS, and multi-GPU communications (NIXL, NCCL, NVSHMEM).
• Represent the team in roadmap and planning discussions, ensuring alignment with NVIDIA’s broader AI and software strategies.
• Foster a culture of technical excellence, open collaboration, and continuous innovation.

Skills

C/C++

Python

GPU programming

Deep learning deployment

Education

MS/PhD or equivalent

Tools

CUDA

Triton

CUTLASS

Job description

NVIDIA is seeking an exceptional Manager, Deep Learning Inference Software, to lead a world-class engineering team focused on deploying AI models with NVIDIA GPUs. The role shapes software powering large language models, multimodal, and generative AI, including open-source frameworks like SGLang, vLLM, and FlashInfer.

You will guide strategy, roadmaps, and end-to-end optimized inference pipelines across accelerators, while mentoring engineers and driving innovation in CUDA, Triton, and multi-GPU