Engineering Manager, Deep Learning Inference

What you'll do

• Lead, mentor, and grow an engineering team focused on deep learning inference and GPU-accelerated software.
• Set strategy, roadmap, and execution for inference framework engineering, with a focus on Client AI.
• Coordinate with compiler, libraries, and research teams to optimize inference pipelines and model performance across NVIDIA accelerators.

What they ask for

• 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 C/C++ software design and development background.
• Hands-on GPU programming experience and performance optimization; production deployment or optimization of deep learning models; experience leading teams using Agile or collaborative practices.

Nice to have

• Significant open-source contributions to deep learning or inference frameworks.
• Expertise in multi-GPU communications, distributed inference, performance modeling, profiling, or system-level optimization.

Pay

184,000 USD - 287,500 USD base salary for Level 2; 224,000 USD - 356,500 USD base salary for Level 3

Tools

C/C++, Python, CUDA, Triton, CUTLASS, NIXL, NCCL, NVSHMEM

AI focus

Leads development and optimization of scalable GPU-accelerated inference frameworks and pipelines for LLM, multimodal, and generative AI models.