Senior Deep Learning Software Engineer, cuDNN

Job Description

We're looking for a Senior Deep Learning Software Engineer to join our cuDNN team at NVIDIA, contributing to the development of GPU-accelerated libraries for deep neural networks.

Requirements

• M.S. Degree in Computer Science, Electrical Engineering (or similar), or equivalent experience
• 4+ years of relevant work or research experience
• Strong programming skills in C/C++, CUDA development, and Python
• Good understanding of linear algebra
• Familiarity with machine learning trends, especially in large language models
• Experience in high-level software architecture design
• Excellent problem-solving skills, including algorithms and data structures
• Experience in performance analysis, profiling, and code optimization
• Ability to work independently, define project goals, and mentor junior engineers

Responsibilities

• Develop production-quality software for NVIDIA's AI software stack, focusing on large language model support
• Analyze and optimize performance of key workloads, proposing improvements for future software
• Collaborate with deep learning software engineers and GPU architects to innovate across various applications
• Adapt to the evolving AI industry by contributing to API design, software architecture, testing, and GPU kernel development
• Mentor junior engineers on the team

Benefits

• Multiple relocation packages
• Two weeklong shutdowns (mid-summer and year-end) in the US (in addition to PTO)
• 8-week parental leave
• 9 Employee Resource Groups
• Annual bonus offering
• Flexible work arrangements
• Up to 6% 401K matching