Engineering Manager, LLM Inference & Deployment at Scale

NVIDIA Gruppe; Santa Clara (CA); Hybrid; USD 224,000 - 431,000; Full time

Benefits offered by this job

Equity

Job summary

NVIDIA is seeking an Engineering Manager to lead a team deploying and serving Large Language Models (LLMs) and Vision‑Language Models (VLMs) at scale. You will guide a platform crossing model optimization, inference systems, and distributed infrastructure to deliver high‑performance production deployments.

You will mentor engineers, collaborate with researchers, and shape the roadmap for scalable AI inference, optimizing latency, throughput, and cost across GPU platforms.

Qualifications

• Master’s or PhD in Computer Science, Computer Engineering, or a related field, or equivalent experience.
• 8+ years total experience, including 3+ years in management/leadership.
• Hands-on experience with LLMs/VLMs and modern DL architectures.
• Expertise in inference optimization techniques: quantization, speculative decoding, batching, KV-cache.

Responsibilities

• Lead, mentor, and grow a high-performing team building and operating a platform for deploying GenAI models at scale.
• Drive deployment and optimization of LLMs and VLMs for low-latency, high-throughput inference.
• Profile and optimize end-to-end DL workloads across model, inference stack, and GPU hardware.
• Collaborate with research teams to bring new architectures from prototype to production.
• Set technical strategy and roadmaps for model deployment, inference optimization, and reliability.
• Establish engineering standards for benchmarking, deployment, and continuous performance optimization.
• Partner with internal and external teams for seamless GenAI model deployment.

Skills

People management

Leadership

Deep learning

Communication

Education

Master's or PhD in CS/CE

Tools

TensorRT

TensorRT-LLM

vLLM

SGLang

Job description

NVIDIA is looking for an Engineering Manager to lead the team responsible for deploying and serving Large Language Models (LLMs) and Vision‑Language Models (VLMs) at scale.

Our team builds and operates an AI inference platform that enables customers to deploy and run brand new generative AI models efficiently across NVIDIA GPU platforms. The platform operates at the intersection of model optimization, inference systems, distributed computing, and production infrastructure.

In this role, you will manage a team of engineers responsible for taking modern models from research and experimentation into highly optimized, reliable, and scalable production deployments. You will work closely with research scientists, software engineers, and hardware specialists to push the boundaries of AI inference performance and deliver a world‑class model deployment platform.

What you will be doing:

• Lead, mentor, and grow a high‑performing team building and operating a platform for deploying GenAI models at scale.
• Drive the deployment and optimization of LLMs and VLMs for low‑latency, high‑throughput, and cost‑efficient inference.
• Analyze, profile, and optimize end‑to‑end deep learning workloads across the model, inference stack, distributed systems, and GPU hardware.
• Work closely with research teams and model developers to bring new architectures and models from prototype to production.
• Drive technical strategy and roadmap for model deployment, inference optimization, scalability, reliability, and performance.
• Establish engineering standards for benchmarking, profiling, production deployment, and continuous performance optimization.
• Collaborate with internal and external partners to enable seamless deployment of rapidly evolving GenAI models.

What we want to see:

• Master’s or PhD in Computer Science, Computer Engineering, or a related field, or equivalent experience.
• 8+ years overall experience, including 3 years of management/leadership.
• Strong hands‑on experience with LLMs and/or VLMs and a solid understanding of modern deep learning architectures.
• Deep expertise in inference optimization techniques such as quantization, speculative decoding, continuous batching, prefix caching, and KV‑cache optimization.
• Experience with disaggregated inference/serving, distributed inference, multi‑node deployments, and GPU cluster orchestration.
• Strong technical leadership, communication, and people‑management skills.

Ways to stand out from the crowd:

• Experience building or operating AI inference, model serving, or model deployment platforms.
• Practical experience in working with TensorRT, TensorRT-LLM, vLLM, SGLang, or comparable inference/serving frameworks.
• Experience building highly available, scalable, and observable production services for AI workloads.

NVIDIA is widely considered to be one of the technology world’s most desirable employers. We have some of the most forward‑thinking and hardworking people in the world working for us. If you're creative and autonomous, we want to hear from you!

#LI-Hybrid

Your base salary will be determined based on your location, experience, and the pay of employees in similar positions. The base salary range is 224,000 USD - 356,500 USD for Level3, and 272,000 USD - 431,250 USD for Level4.

You will also be eligible for equity and benefits.

Applications for this job will be accepted at least until September1,2026.

This posting is for an existing vacancy.

NVIDIA uses AI tools in its recruiting processes.

NVIDIA is committed to fostering an inclusive work environment and proud to be an equal opportunity employer. As we highly value diversity in our current and future employees, we do not discriminate (including in our hiring and promotion practices) on the basis of race, religion, color, national origin, gender, gender expression, sexual orientation, age, marital status, veteran status, disability status or any other characteristic protected by law.