2 months ago
Shenzhen, China or Beijing, ChinaMid Level
Responsibilities
- Design, deploy, and optimize large-scale LLM and Agentic AI inference systems on NVIDIA accelerated computing platforms.
- Analyze end-to-end inference workloads to improve latency, throughput, scalability, resource utilization, and cost efficiency.
- Develop solutions involving KV cache management, intelligent routing and scheduling, distributed or disaggregated serving, heterogeneous inference, and large-scale model parallelism.
- Build proof-of-concepts, performance studies, and reference solutions for emerging AI architectures.
- Collaborate with NVIDIA Engineering, Product, Sales, and Business Development teams to address customer needs, provide product feedback, and shape technical strategies.
Requirements
- MS or PhD in Electrical Engineering, Computer Science or Computer Engineering, Mathematics, Physics, or a related field, or equivalent practical experience.
- At least 3 years of relevant experience in large language models, AI inference, distributed AI systems, or related areas.
- Hands-on experience with system design, performance optimization, or large-scale AI workloads.
- Strong understanding of modern AI systems and performance analysis across models, software frameworks, compute, memory, communication, and infrastructure.
- Strong programming, problem-solving, technical communication, and stakeholder collaboration skills.
- Experience with Agentic AI, advanced LLM inference optimization, GPU-accelerated workloads, distributed computing platforms, NVIDIA AI software, cloud service providers, or production AI infrastructure is preferred.
- Familiarity with NVIDIA Dynamo, TensorRT-LLM, disaggregated serving, heterogeneous inference, expert parallelism, or other large-scale serving techniques is preferred.
Benefits
- The role involves working with advanced computing hardware and software and collaborating with leading cloud service providers, AI platform teams, researchers, engineers, and senior technical leaders.
- NVIDIA offers a diverse and equal-opportunity work environment.
Categories
Solutions Engineering
About Nvidia
Nvidia designs and sells GPUs and accelerated computing platforms for data centers, AI/ML, graphics, gaming, and automotive, monetizing through hardware, software platforms (CUDA, AI frameworks), and systems like DGX and networking. Customers include cloud providers, enterprises, researchers, and OEMs. Founded in 1993 and headquartered in Santa Clara, it is a public company traded on NASDAQ under NVDA.