Deep Learning Solutions Architect – Inference Optimization - Remote

Overview

NVIDIA’s Worldwide Field Operations (WWFO) team is seeking a Solution Architect with a deep understanding of neural network inference. The ideal candidate will be proficient using tools such as TRT LLM, vLLM, SGLang or similar, and have strong systems knowledge, enabling customers to fully use the capabilities of the new GB300 NVL72 systems.

In Short

• Work directly with key customers to understand their technology and provide the best AI solutions.
• Perform in-depth analysis and optimization on GPU architecture systems.
• Partner with Engineering, Product, and Sales teams to develop suitable solutions for customers.
• Enable development and growth of product features through customer feedback.
• Engage with developers, researchers, data scientists, and IT managers.
• Demonstrate excellent communication and technical presentation skills.
• 5+ years of experience with Python/C++ and modern NLP.
• Experience with key libraries for NLP/LLM training and deployment.
• Collaborate with various teams in a dynamic environment.
• Passion for continuous learning and sharing findings across the team.

Requirements

• MS/PhD or equivalent experience in a relevant field.
• 5+ years of work or research experience in software development.
• Understanding of transformer and diffusion model architectures.
• Familiarity with DevOps tools including Docker and Kubernetes.
• Experience with HPC systems and data center design.
• Ability to thrive in dynamic environments.
• Self-starter with a passion for growth and continuous learning.
• Experience in running and debugging large-scale deep learning processes.
• Applied NLP technology in production environments.
• Strong interpersonal skills to engage with various stakeholders.

Benefits

• Highly competitive salaries.
• Comprehensive benefits package.
• Diverse work environment.
• Opportunities for growth and development.
• Work with cutting-edge technology in AI.