Deep Learning Software Engineer, Inference and Model Optimization - New College Grad 2025

This role is based in Santa Clara, CA or can be performed remotely.

Compensation:

$120,000 - $189,750/year

Responsibilities:

• Train, develop, and deploy generative AI models using NVIDIA's AI software stack.
• Develop high-performance optimization techniques for inference.
• Collaborate with teams across NVIDIA to enhance automated deployment solutions.
• Analyze GPU kernel-level performance for optimization opportunities.

Requirements:

• Masters, PhD, or equivalent experience in Computer Science, AI, Applied Math, or related field.
• Experience in Deep Learning and strong proficiency in Python and PyTorch.
• Excellent software design skills and debugging abilities.

Tech stack:

Python, PyTorch, CUDA, TRT-LLM, Triton.