Distributed AI Inference Performance Engineer

NVIDIA Gruppe; Santa Clara (CA); On-site; USD 120,000 - 160,000; Full time

Job summary

NVIDIA Gruppe in Santa Clara is looking for an engineer to optimize and benchmark GenAI inference on cutting-edge accelerators. This role involves owning end-to-end optimization pipelines and defining next-generation inference benchmarks across multiple platforms.

The ideal candidate will have a strong background in software development, particularly in Python or C++, and a deep understanding of LLM/VLM architectures. Join our team to influence the ecosystem and contribute to impactful open-source projects.

Qualifications

• 2+ years of relevant software development experience.
• Strong skills in Python or C++ programming and software design.
• Deep understanding of LLM/VLM architectures and inference mechanics.

Responsibilities

• Drive industry benchmark results and own the optimization pipeline.
• Define next-generation inference benchmarks and shape AI use cases.
• Design distributed inference across GPU clusters.

Skills

Python programming

C++ programming

Software design

Software engineering

Deep Learning frameworks (e.g., PyTorch, JAX)

Education

BS, MS, or PhD in Computer Science, Computer Engineering, Electrical Engineering

Job description

NVIDIA Gruppe in Santa Clara is looking for an engineer to optimize and benchmark GenAI inference on cutting-edge accelerators. This role involves owning end-to-end optimization pipelines and defining next-generation inference benchmarks across multiple platforms.

The ideal candidate will have a strong background in software development, particularly in Python or C++, and a deep understanding of LLM/VLM architectures. Join our team to influence the ecosystem and contribute to impactful open-source projects.