Logo of Huzzle

Deep Learning Performance Architect

image

NVIDIA

1mo ago

  • Job
    Full-time
    Junior Level
  • Data
    Software Engineering

AI generated summary

  • You need an MS/PhD in CS, EE, or Math, 2+ years in parallel computing/deep learning, strong C/C++/Python skills, and expertise in architecture analysis and performance modeling.
  • You will benchmark AI workloads, develop simulators in C++/Python, analyze PPA for hardware features, collaborate on architectural trade-offs, and stay updated on deep learning trends.

Requirements

  • MS or PhD in a relevant discipline (CS, EE, Math).
  • 2+ years of experience in parallel computing architectures, interconnect fabrics and deep learning applications.
  • Strong programming skills in C, C++ and Python.
  • Proficiency in architecture analysis and performance modeling.
  • Curious mindset with excellent problem solving skills.

Responsibilities

  • Benchmark and analyze AI workloads in single and multi-node configurations.
  • High level simulator and debugger development in C++/Python.
  • Evaluate PPA (performance, power, area) for hardware features and system-level architectural trade-offs.
  • Work closely with wider architecture teams, architecture and product management to help with trade-off analysis at every stage of the project.
  • Keep abreast with emerging trends and research in deep learning.

FAQs

What is the primary focus of the Deep Learning Performance Architect position at NVIDIA?

The primary focus is to benchmark and analyze AI workloads, develop high-level simulators and debuggers, and evaluate hardware features and system-level architectural trade-offs for deep learning applications.

What qualifications are required for the Deep Learning Performance Architect role?

Candidates should have an MS or PhD in a relevant discipline such as Computer Science, Electrical Engineering, or Mathematics, along with 2+ years of experience in parallel computing architectures and deep learning applications.

What programming languages are essential for this position?

Strong programming skills in C, C++, and Python are essential for this position.

Is it necessary to have experience in architecture analysis and performance modeling?

Yes, proficiency in architecture analysis and performance modeling is a key requirement for this role.

What kind of interpersonal skills are important for this job?

A curious mindset with excellent problem-solving skills is important, along with the ability to simplify and communicate rich technical concepts to a non-technical audience.

What additional skills can help a candidate stand out for this position?

Understanding modern transformer-based model architectures, experience with benchmarking, workload profiling, and the ability to communicate complex technical concepts are qualities that can help candidates stand out.

Will I need to keep up with developments in the field of deep learning?

Yes, candidates are expected to keep abreast of emerging trends and research in deep learning as part of their responsibilities.

What is the work environment like at NVIDIA?

NVIDIA offers a diverse and supportive environment where team members are inspired to do their best work, focusing on innovation and making a lasting impact.

Are there opportunities to collaborate with other teams within the company?

Yes, the role involves working closely with wider architecture teams, architecture, and product management to assist with trade-off analysis at various stages of projects.

Manufacturing & Electronics
Industry
10,001+
Employees
1993
Founded Year

Mission & Purpose

Since its founding in 1993, NVIDIA (NASDAQ: NVDA) has been a pioneer in accelerated computing. The company’s invention of the GPU in 1999 sparked the growth of the PC gaming market, redefined computer graphics, ignited the era of modern AI and is fueling the creation of the metaverse. NVIDIA is now a full-stack computing company with data-center-scale offerings that are reshaping industry.