Deep Learning Performance Architect

NVIDIA is seeking a Deep Learning Performance Architect to join its team. As a Deep Learning Performance Architect, you will develop innovative hardware architectures to extend the state of the art in parallel computing performance and energy efficiency.

Responsibilities:

• Develop innovative HW architectures to extend the state of the art in parallel computing performance and energy efficiency.
• Benchmark and analyse AI workloads in single and multi-node configurations.
• Develop tools to profile, analyse and debug parallel applications in Python/C++.
• Work closely with peer architecture teams and product management to guide development of the products.
• Keep abreast with emerging trends and research in deep learning.

Requirements:

• B.Tech. or M.Tech. in a relevant discipline (CS, EE, Math).
• 1+ years of experience in C, C++ and Python.
• Curious mindset with excellent problem-solving skills.

Preferred qualifications:

• Familiarity with GPU computing and parallel programming.
• Understanding of modern transformer-based model architectures.
• Experience with architecture simulator development, performance modelling, profiling, and analysis.