Senior AI Training Performance Engineer

NVIDIA·Shanghai, Shanghai, China·posted 57d ago · last seen 1h ago

Track this application

Get Started Free

Match score against your CV

Get Started Free

Tailor your resume to this job

Get Started Free

About interviewing at NVIDIA

Recruiter screen, a technical screen mixing resume deep-dive with live coding, a hiring-manager conversation, then a panel of three to five 45–60 minute rounds: coding, systems design under hardware constraints, a domain deep-dive, and behavioral. Highly team-specific — you interview directly with the team — with C++ depth expected almost universally and decisions sometimes taking five-plus weeks after the panel.

Read the full NVIDIA interview process →

Description

We are now looking for a Senior AI Training Performance Engineer!

NVIDIA is seeking senior engineers who are obsessed with performance analysis and optimization to help us squeeze every last clock cycle out of AI training, one of the most important workloads in the world. If you are unafraid to work across all layers of the hardware/software stack from GPU architecture to Deep Learning Framework to achieve peak performance, we want to hear from you! This role offers the opportunity to directly impact the hardware and software roadmap in a fast-growing technology company that leads the AI revolution while helping deep learning users around the globe enjoy ever-higher training speeds.

What you will be doing:

  • Understand, analyze, profile, and optimize AI and deep learning training workloads on state-of-the-art hardware and software platforms.

  • Understand the big picture of training performance on GPUs, prioritizing and then solving problems across many dozens of state-of-the-art neural networks.

  • Implement production-quality software in multiple layers of NVIDIA's deep learning platform stack, from drivers to DL frameworks.

  • Implement key DL training workloads in NVIDIA's proprietary processor and system simulators to enable future architecture studies.

  • Build tools to automate workload analysis, workload optimization, and other critical workflows.

What we want to see:

  • PhD (or equivalent experience) in CS, EE or CSEE and 5+ years; or MS and 8+ years of relevant work experience.

  • Strong background in deep learning and neural networks, in particular training.

  • Deep understanding of computer architecture, and familiarity with the fundamentals of GPU architecture.

  • Proven experience analyzing and tuning application performance.

  • Experience with processor and system-level performance modelling.

  • Programming skills in C++, Python, and CUDA.

  • Fluency in English

NVIDIA is increasingly known as the AI Computing company and is widely considered to be one of the technology world’s most desirable employers. We have some of the most forward-thinking and hardworking people on the planet working for us. Are you passionate about performance? Are you interested in working on industry-leading Deep Learning products? Come, join our Deep Learning Architecture team, where you can help build real-time, cost-effective computing platforms driving our success in this exciting and rapidly growing field.

More engineering roles at NVIDIA