Nvidia Engineering Manager Deep Learning Inference 

United States, Texas 

850503382

What you'll be doing:

• Lead, mentor, and scale a high-performing engineering team focused on deep learning inference and GPU-accelerated software.

• Drive the strategy, roadmap, and execution of NVIDIA’s inference frameworks engineering, focusing on SGLang.

• 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.

What we need to see:

• MS, PhD, or equivalent experience in Computer Science, Electrical/Computer Engineering, or a 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.

Ways to Stand out from The Crowd

• Significant open-source contributions to deep learning or inference frameworks such as PyTorch, vLLM, SGLang, Triton, or TensorRT-LLM.

• Deep understanding of multi-GPU communications (NIXL, NCCL, NVSHMEM) and distributed inference architectures.

• Expertise in performance modeling, profiling, and system-level optimization across CPU and GPU platforms.

• Proven ability to mentor engineers, guide architectural decisions, and deliver complex projects with measurable impact.

• Publications, patents, or talks on LLM serving, model optimization, or GPU performance engineering.