Engineering Manager, LLM Performance

At NVIDIA, we aren't just powering the AI revolution—we're accelerating it. We are accelerating LLM inference across the stack and across all open source LLM frameworks like TensorRT LLM, vLLM and SGLang. With demand for AI exploding, particularly in the realm of large language models (LLMs) and vision language models (VLMs, VLAs), we are significantly expanding our team. 

We're seeking a highly skilled and driven Engineering Manager to take the lead in accelerating the next generation of LLM/VLM/VLA inference software technologies that will define the future of AI. This is a high-impact, hands-on leadership role at the intersection of deep technical expertise and world-class management. You won't just manage; you'll architect and guide a brilliant team of engineers who are pushing the performance of LLM inference. Your work will be highly collaborative, interfacing directly with NVIDIA Researchers, GPU Architects, and other teams across the company to ensure we ship production-grade, lightning-fast software that sets the global standard for AI performance. 

What You’ll Be Doing: 

• Lead and grow a team responsible for pushing the performance of LLM inference across multiple LLM frameworks, including TensorRT LLM, vLLM, SGLang and Dynamo on our datacenter products. 

• Drive the design, implementation and optimization of features that are key to performance in LLM inference. 

• Continuously improve the performance of LLM inference on current and upcoming NVIDIA datacenter architectures and GPUs. 

• Continuously improve the performance of LLM inference of important foundation models.  

• Work with inference benchmark teams to help tune performance for key workloads. 

• Integrating cutting-edge technologies developed at NVIDIA and offering an intuitive developer experience for LLM deployment. 

• Lead software development execution, with responsibility for project planning, milestone delivery, and cross-functional coordination. 

What We Need to See: 

• MS, PhD, or equivalent experience in Computer Science, Computer Engineering, AI, or a related technical field. 

• 7+ overall years of overall software engineering experience, including 3+ years of technical leadership experience. 

• Proven ability to lead and scale high-performing engineering teams, especially across distributed and cross-functional groups. 

• Strong background in C++ or Python, with expertise in software design and delivering production-quality software libraries. 

• Demonstrated expertise in large language models (LLM) and/or vision language models (VLM) and/or inference in general. 

Ways to Stand Out from the Crowd: 

• Deep understanding of GPU architecture, CUDA programming, and system-level performance tuning. 

• Background in LLM inference or working with frameworks such as TensorRT-LLM, vLLM, or SGLang. 

• Passion for building scalable, user-friendly APIs and enabling developers in the AI ecosystem. 

• Have a proven track record of growing and managing a team that encourages idea sharing, empowers team members, and provides opportunities for professional growth.