Principal Software Engineer, TensorRT-LLM

Details

We are now looking for a Principal Software Engineer to join the TensorRT-LLM team at NVIDIA. The team builds AI serving software used across NVIDIA and the industry. The role requires working on a fast-paced, delivery-focused team and collaborating across software, research, and product teams to guide the direction of AI inferencing.

Responsibilities

• Architect and guide development of robust inferencing software that can be scaled to multiple platforms for functionality and performance.
• Perform performance analysis, optimization, and tuning.
• Closely follow developments in the field of artificial intelligence and evolve code design to keep pace.
• Collaborate across the company with software, research, and product teams to guide AI inferencing direction.

Requirements

• Bachelor’s, Master’s, or higher degree in Computer Engineering, Computer Science, Applied Mathematics, or a related computing-focused degree (or equivalent experience).
• 15+ years of relevant software development experience and 2+ years in an architect/tech lead role.
• Excellent Python or C/C++ programming and software design skills, including debugging, performance analysis, and test design.
• Strong understanding of GenAI serving and awareness of the latest developments in deep learning such as large language models (LLMs).
• Experience working with LLM inference frameworks like vLLM, SGLang, etc.
• Experience working with deep learning frameworks like PyTorch and JAX.
• Excellent written and oral communication skills in English.

Benefits and Additional Information

• Base salary range: 272,000 USD - 425,500 USD (determined based on location, experience, and pay of employees in similar positions).
• Eligible for equity and company benefits.
• Applications for this job will be accepted at least until July 29, 2025.
• NVIDIA is an equal opportunity employer and committed to fostering a diverse work environment.
• #LI-Hybrid