Senior GPU AI Platform Engineer — Edge Inference (Equity)

NVIDIA AI; Seattle (WA); On-site; USD 224,000 - 431,250; Full time

Benefits offered by this job

Equity

Benefits

Job summary

NVIDIA is seeking a seasoned engineer to advance LLM inference on edge AI hardware. You’ll evaluate frameworks, map model architectures to GPU, and optimize across multi-node deployments, focusing on performance and stability.

You’ll own validation workflows, develop actionable recipes, and collaborate with the community and partners to resolve hardware-specific inference issues. Equity and benefits are offered.

Qualifications

• BS, MS, or PhD in Computer Science, Computer Engineering, Electrical Engineering, or equivalent experience.
• 12+ years of software engineering with depth in GPU computing, ML systems, or high-performance inference.
• Strong Python or C++ programming, software design, and software engineering skills.

Responsibilities

• Track and evaluate innovations in open-source LLM inference frameworks and identify performance features.
• Map new model architectures and inference algorithms to NVIDIA GPU architecture and optimize.
• Characterize multi-node inference behavior and topology-aware all-reduce strategies on edge clusters.
• Publish performance analyses mapping hardware limits to observed throughput, latency, and utilization.
• Own the model validation workflow for new model releases and develop inference recipes.
• Develop and maintain developer-facing inference recipes, automate staleness detection, and update CI results.
• Engage with community and partners on model bring-up questions; act as technical point of contact for hardware-specific inference issues.

Skills

Python

C++

GPU computing

ML systems

Performance optimization

Education

BS/MS/PhD in CS/CE/EE or related field

Tools

CUDA

Triton

Job description

NVIDIA is seeking a seasoned engineer to advance LLM inference on edge AI hardware. You’ll evaluate frameworks, map model architectures to GPU, and optimize across multi-node deployments, focusing on performance and stability.

You’ll own validation workflows, develop actionable recipes, and collaborate with the community and partners to resolve hardware-specific inference issues. Equity and benefits are offered.