Solution Architect - Agentic AI - CSP

Responsibilities

• Work with customers to design, deploy, and optimize large-scale LLM and Agentic AI inference systems on NVIDIA accelerated computing platforms.
• Analyze end-to-end inference workloads and identify opportunities to improve latency, throughput, scalability, resource utilization, and cost efficiency.
• Explore and develop solutions for emerging Agentic AI inference challenges, which may include areas such as 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 to validate new architectures and demonstrate the value of NVIDIA technologies in real-world AI workloads.
• Partner with NVIDIA Engineering, Product, Sales, and Business Development teams to solve customer problems, provide product feedback, and help shape technical strategies for strategic AI infrastructure opportunities.
• What we need to see
• MS or PhD in Electrical Engineering, Computer Science/Engineering, Mathematics, Physics, or a related field, or equivalent practical experience.
• 3+ years of relevant experience in large language models, AI inference, distributed AI systems, or related areas, with hands-on experience in system design, performance optimization, or large-scale AI workloads.
• Strong understanding of modern AI systems and the ability to analyze performance across models, software frameworks, compute, memory, communication, and infrastructure.
• Strong programming and problem-solving skills, with experience using common AI frameworks and tools. Proficiency in using AI tools or agents to improve engineering productivity is highly valued.

Languages