Distinguished Software Architect - Deep Learning and HPC Communications

Job Description

NVIDIA is seeking a Distinguished Software Architect to co-design next-generation data center platforms for High Performance Computing and Deep Learning applications.

Requirements

• PhD in Computer Science, Computer Engineering or related field
• Expertise in HPC, parallel programming models, communication runtimes, computer and system architecture, GPU architecture, CUDA
• Deep understanding of high performance networking
• Programming fluency in C or C++
• Experience in ML/DL fundamentals, parallel algorithms, fault tolerance, performance analysis, DL Frameworks
• Ability to work across different HW/SW teams and timezones
• Industry recognition in HPC/DL communications and standards

Responsibilities

• Research new communication technologies and design features for communication libraries
• Propose innovative solutions in HW and SW for next-gen platforms
• Collaborate with GPU, Networking, and SW architects
• Inspire changes based on quantitative data
• Drive adoption of new communication technologies
• Keep up with latest DL research and collaborate with diverse teams

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