Engineering Manager, AI Inference & GPU Scaling

NVIDIA Corporation; Santa Clara (CA); Hybrid; USD 184,000 - 357,000; Full time

Benefits offered by this job

Equity

Comprehensive benefits

Hybrid work model

Job summary

NVIDIA Corporation is seeking a Manager of Deep Learning Inference Software to lead a world-class team advancing AI model deployment on NVIDIA GPUs. You will drive strategy, mentoring, and execution of inference frameworks for Client AI, collaborating across compiler, libraries, and research groups.

You will oversee performance tuning for large models (LLM, multimodal, generative AI), using CUDA, Triton, and multi-GPU communications. Equity and comprehensive benefits are offered.

Qualifications

• MS/PhD in Computer Science, Electrical/Computer Engineering, or related field.
• 6+ years software development, 3+ years leadership or management.
• Strong C/C++ design; Python a plus.

Responsibilities

• Lead and scale a high-performing team focused on deep learning inference and GPU-accelerated software.
• Drive strategy, roadmaps, and execution of inference frameworks for Client AI.
• Collaborate with compiler, libraries, and research teams to deliver optimized inference pipelines.

Skills

C/C++ development

GPU programming

CUDA

Triton

CUTLASS

Python

Performance optimization

DL inference

Distributed systems

Education

MS/PhD in CS/EE

Tools

NCCL

NVSHMEM

Triton

CUTLASS

TensorRT

Job description

NVIDIA Corporation is seeking a Manager of Deep Learning Inference Software to lead a world-class team advancing AI model deployment on NVIDIA GPUs. You will drive strategy, mentoring, and execution of inference frameworks for Client AI, collaborating across compiler, libraries, and research groups.

You will oversee performance tuning for large models (LLM, multimodal, generative AI), using CUDA, Triton, and multi-GPU communications. Equity and comprehensive benefits are offered.