Performance Engineer, Deep Learning

Nvidia

Confirmed live today High trust

Quick summary

Work type: On-site
Location: Santa Clara, CA
Salary: $124,000–$195,500 / yr
Employment: Full-time
Posted: 4 days ago
Freshness: Confirmed live today
Nearby: 99+ roles within 25 mi

Market check

Salary context

Below market

How this pay compares to similar roles

Similar $217k

This role $160k

$107k $280k

below market most similar roles pay here above market

This role pays less than 92% of similar roles. Most pay $187,850–$246,150 — the blue band above. At the midpoint, this role pays about $160k versus about $217k for comparable roles.

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 1448 open roles on FindRole.

Listed pay typically runs $184,000–$287,500 across 1088 roles with salary data.

Most-posted roles

View all roles at Nvidia

At a glance

TL;DR · Performance Engineer, Deep Learning

Role Posting Log in to save

Performance Engineer - Deep Learning joins the Deep Learning models performance engineering team to build and optimize libraries and tools for designing and deploying efficient AI applications. You will build and support the Transformer Engine open-source library to accelerate Large Language Model training while collaborating on systems research regarding low precision training and parallelism methods. Responsibilities include implementing, benchmarking, and optimizing new models to scale on GPUs, contributing to MLPerf benchmarks, and influencing future hardware designs. The role requires proficiency in C++ and Python, with a strong background in parallel systems programming, computer architecture, and code optimization. Candidates should possess experience with PyTorch, JAX, and GPU kernels using CUDA, OpenAI Triton, CuTeDSL, or Pallas to solve complex performance bottlenecks within mainstream open-source Deep Learning frameworks.

Skills

C++ Python PyTorch JAX CUDA OpenAI Triton cuBLAS cuDNN cuSOLVER Parallel Systems Deep Learning LLMs Computer Architecture Code Optimization Operating Systems MLPerf Transformer Engine

What you'll do

Build and support the Transformer Engine library for accelerating Large Language Model training.
Implement and optimize new Deep Learning models to scale efficiently on NVIDIA GPUs and systems.
Collaborate on systems research to improve performance through low precision training and parallelism methods.
Build and contribute to NVIDIA submissions for community benchmarks like MLPerf.
Influence the design of new hardware generations and core platform software components.
Support enterprise customers and partners by delivering NVIDIA’s latest hardware and software innovations.
Contribute optimizations directly into mainstream open-source frameworks like PyTorch and JAX.

What we're looking for

BS or equivalent experience in Computer Science, Electrical Engineering, or a related field.
2+ years of experience in C++ and Python programming.
Strong background, experience, or coursework in parallel systems programming, preferably on GPUs (preferred).
Knowledge of Computer Architecture, Code Optimization, and/or Operating Systems.
Proven experience in developing large software projects.
Excellent verbal and written communication skills.
Experience in PyTorch, JAX, or any other DL framework (preferred).
Experience with performance analysis, profiling, and code optimization techniques, especially with multi-GPU or multi-node systems (preferred).