Manager, GPU Accelerated Data Analytics

NVIDIA NVIDIA · Semiconductors · Santa Clara, CA +3 · Remote

Manager for a team of performance engineers focused on optimizing CPU and GPU performance for data analytics workloads, including database, data preprocessing, and video transcoding, using NVIDIA's platform. The role involves researching and developing new algorithms and techniques to improve performance and reduce cost/power, leading software design decisions, influencing architecture, and mentoring the team. Requires strong C/C++ programming, CUDA, CPU/GPU architecture expertise, and leadership experience.

What you'd actually do

  1. Driving Innovation: This involves researching, analyzing, and developing innovative techniques to optimize performance of complex workloads across cloud and on-premise environments.
  2. Technical Leadership: Drive technical excellence by leading software design decisions, influencing architecture roadmap, and effectively communicating technical solutions to multi-functional teams.
  3. Growing and Mentoring Your Team: Build a distributed world-class team of performance engineers.
  4. Collaboration and Communication: Collaborate closely with company leadership, research teams, and cross-functional partners to drive strategic decision-making, program management, and successful initiative implementation.

Skills

Required

  • MS or PhD in Computer Science, Computer Engineering, or related field (or equivalent experience)
  • 7+ years of relevant experience
  • 4+ years in a technical role
  • 3+ years in an engineering leadership role
  • Outstanding leadership
  • Strong cross-functional collaboration
  • Impactful project execution
  • Hands-on experience in low-level performance optimization
  • GPU parallel programming
  • CUDA
  • Programming fluency in C/C++
  • Deep understanding of algorithms and software development
  • In-depth expertise with CPU and GPU architecture fundamentals
  • Strong algorithmic skills
  • Proven experience implementing low-level optimizations for enterprise applications
  • Track record of building high-performing teams
  • Attracting and hiring top engineering talent
  • Excellent communication and presentation skills
  • Demonstrated ability to successfully plan, lead, and execute high-impact initiatives

Nice to have

  • PhD in a relevant field
  • Experience leading engineering teams to design performance-first prototypes
  • Strong background in distributed high-performance data analytics including SQL or vector databases
  • Expertise in modern data center network and storage technologies

What the JD emphasized

  • researching, analyzing, and developing innovative techniques to optimize performance
  • inventing new algorithms
  • low-level performance optimization
  • GPU parallel programming
  • CUDA
  • CPU and GPU architecture fundamentals
  • algorithmic skills
  • building high-performing teams