Senior DL Inference Engineer — GPU-Accelerated AI

NVIDIA; Texas; On-site; USD 152,000 - 288,000; Full time

Benefits offered by this job

Equity

Benefits

Career growth

Job summary

NVIDIA seeks a Senior Software Engineer specializing in Deep Learning Inference to design, build, and optimize GPU-accelerated software powering today’s AI applications.

You will work with open-source frameworks, implementing the latest inference algorithms and driving performance improvements across datacenter GPUs and edge devices. Collaboration across teams will accelerate deployment of cutting-edge language models.

Qualifications

• Masters or PhD or equivalent experience in Computer Engineering, Computer Science, EECS, AI.
• 5+ years of relevant software development experience.
• Strong C/C++ programming and software design skills; Python a plus.
• Experience with training, deploying or optimizing inference of DL models in production is a plus.
• Background with performance modeling, profiling, debugging and code optimization for CPU/GPU is a plus.
• GPU programming experience (CUDA, OAI TRITON or CUTLASS) is a plus.

Responsibilities

• Performance optimization, analysis, and tuning of DL models in contexts like LLMs, Multimodal and Generative AI.
• Scale performance of DL models across architectures and NVIDIA accelerators.
• Contribute features and code to NVIDIA’s inference libraries and related software solutions.
• Collaborate with cross-functional teams across frameworks, libraries, and inference optimization.

Skills

C/C++ programming

Python experience

CUDA

GPU programming

Performance optimization

Deep learning inference

Software design

Education

Masters or PhD

Equivalent experience

Tools

CUTLASS

OAI Triton

NCCL

CUDA kernels

vLLM

SGLang

PyTorch

Job description

NVIDIA seeks a Senior Software Engineer specializing in Deep Learning Inference to design, build, and optimize GPU-accelerated software powering today’s AI applications.

You will work with open-source frameworks, implementing the latest inference algorithms and driving performance improvements across datacenter GPUs and edge devices. Collaboration across teams will accelerate deployment of cutting-edge language models.