Senior Performance Architect

Nvidia

Confirmed live today High trust

Quick summary

Work type: On-site
Location: Santa Clara, CAHillsboro, ORRedmond, WA
Employment: Full-time
Posted: 161 days ago
Freshness: Confirmed live today
Nearby: 99+ roles within 25 mi

Market check

Salary context

How this pay compares to similar roles

Similar $217k

$160k $276k

below market most similar roles pay here above market

This listing doesn't post a salary. Most similar roles pay $187,250–$245,925.

Based on 240 similar postings.

Employer

About Nvidia

Nvidia is a leading designer of graphics processing units (GPUs) and system-on-chip units, powering gaming, professional visualization, data centers, and artificial intelligence workloads. Industry: Semiconductors & AI Computing

Nvidia currently has 1623 open roles on FindRole.

Listed pay typically runs $184,000–$287,500 across 1110 roles with salary data.

Most-posted roles

View all roles at Nvidia

At a glance

TL;DR · Senior Performance Architect

Role Posting Log in to save

JOB TITLE: Senior Performance Architect, Nemotron The Senior Performance Architect, Nemotron joins the team to shape the next generation of Nemotron models through performance modeling, analysis, and forward projections. You will develop high-fidelity analytical models to prototype emerging algorithmic techniques and hardware optimizations, ensuring models achieve Pareto-optimal trade-offs across accuracy, throughput, and interactivity. Daily responsibilities include modeling end-to-end performance impacts for GenAI workflows like Speculative Decoding, Agentic Pipelines, and RL to understand future datacenter needs. You will utilize Python, C++, and deep learning frameworks including PyTorch, TRT-LLM, VLLM, and SGLang. The role requires expertise in computer architecture, roofline modeling, queuing theory, and statistical performance analysis. You will collaborate across research, compiler, and hardware teams to solve the technical problem of how efficiently intelligence scales in production environments.

Skills

Python C++ PyTorch TRT-LLM VLLM SGLang CUDA GPU Computing Deep Learning Model Parallelism Inference Serving Roofline Modeling Queuing Theory Statistical Performance Analysis Performance Modeling Speculative Decoding RL Agentic Pipelines

What you'll do

Develop high-fidelity analytical performance models to prototype emerging algorithmic techniques and hardware optimizations.
Predict how architectural choices translate into real-world deployment efficiency for the Nemotron model family.
Ensure models achieve Pareto-optimal trade-offs across accuracy, throughput, and interactivity on target platforms.
Prioritize software and hardware roadmap features based on detailed performance modeling and analysis.
Model end-to-end performance impacts of emerging GenAI workflows like Speculative Decoding and Agentic Pipelines.
Identify resource bottlenecks by defining metrics, designing experiments, and visualizing large performance datasets.
Guide model-hardware co-design decisions to determine how efficiently intelligence scales in production.

What we're looking for

Master's degree or equivalent experience in Computer Science, Electrical Engineering, or a related field.
Strong background in computer architecture, roofline modeling, queuing theory, and statistical performance analysis.
Solid understanding of ML fundamentals, model parallelism, and inference serving techniques.
Proficiency in Python for simulator design and data analysis.
Proficiency in C++ (preferred).
3+ years of hands-on experience in system evaluation of AI/ML workloads or performance analysis, modeling, and optimizations for AI.
Experience with deep learning frameworks like PyTorch, TRT-LLM, VLLM, or SGLang.
Experience with GPU computing (CUDA) (preferred).

Save