Senior Deep Learning Performance Architect

NVIDIA

Base: 184,000 usd - 287,500 usd; bonus/equity: equ...
Develop innovative hw architectures
Mathematical frameworks for system availability
Deep learning workload performance analysis
Develop innovative HW architectures to extend the state of the art in parallel computing performance, energy efficiency and programmability

Job Summary

  • Develop innovative HW architectures to extend the state of the art in parallel computing performance, energy efficiency and programmability.
  • Conduct "what-if" studies on hardware configurations, infrastructure knobs, and workload strategies to identify optimal system-level trade-offs.
  • Work closely with wider architecture and product teams to guide the hardware/software roadmap using data-driven performance and reliability projections.

Matching Summary

Develop innovative HW architectures to extend the state of the art in parallel computing performance, energy efficiency and programmability.

Salary

Base: 184,000 USD - 287,500 USD; Bonus/Equity: equity; Benefits: benefits

Skills & Requirements

Must-have

  • Develop innovative HW architectures
  • Mathematical frameworks for system availability
  • Deep Learning workload performance analysis
  • High-level simulators in Python
  • Analytical and probabilistic modeling

Nice-to-have

  • Troubleshoot large-scale jobs
  • Operational datasets
  • Orchestrator knowledge
  • Communicate technical concepts

Key Requirements

  • MS or PhD or equivalent experience
  • 6+ years relevant industry or research experience
  • 2+ years parallel computing architectures experience
  • Understanding of distributed deep learning workloads scheduling
  • Proficiency in Python for modeling

Work Rights

Not specified

Tailored Resume

Cover Letter