Remote Deep Learning Inference Engineering Lead

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

Benefits offered by this job

Equity

Benefits

Hybrid work arrangement

Job summary

NVIDIA Corporation seeks an Engineering Manager for Deep Learning Inference to lead a high-performing team focused on GPU-accelerated inference software. You will shape strategy, roadmaps, and end-to-end optimization of inference pipelines across NVIDIA accelerators.

The role requires strong C/C++ design, GPU programming with CUDA/Triton, and a track record of deploying DL models in production. Hybrid/remote options apply, with a competitive compensation package.

Qualifications

• MS/PhD or equivalent in CS/EE or related field.
• 6+ years software development, with 3+ years in leadership.
• Strong C/C++ design; Python is a plus.
• Hands-on GPU programming (CUDA) and performance optimization.
• Experience deploying DL inference in production.

Responsibilities

• Lead, mentor, and scale the inference software team.
• Define strategy, roadmap, and execution for inference frameworks.
• Collaborate with compiler, libraries, and research teams.
• Oversee performance tuning for large-scale models on GPUs.
• Promote best practices for CUDA, Triton, and multi-GPU comms.

Skills

C/C++

Python

CUDA

Triton

NCCL

Education

MS/PhD in CS/EE

Tools

CUDA Toolkit

Triton

CUTLASS

NCCL

NVSHMEM

Job description

NVIDIA Corporation seeks an Engineering Manager for Deep Learning Inference to lead a high-performing team focused on GPU-accelerated inference software. You will shape strategy, roadmaps, and end-to-end optimization of inference pipelines across NVIDIA accelerators.

The role requires strong C/C++ design, GPU programming with CUDA/Triton, and a track record of deploying DL models in production. Hybrid/remote options apply, with a competitive compensation package.