Solution Architect - Agentic AI - CSP
Core
Design, deploy, and optimize large-scale LLM and Agentic AI inference systems on NVIDIA accelerated computing platforms for cloud service providers and AI platform teams.
Role type
Senior IC Solutions Architect (Agentic AI Inference)
Builds
Scalable, responsive, and cost-efficient AI inference infrastructure and reference solutions
Domain
Cloud computing + AI inference optimization
Deliverable
production ML models
Required skills
Large language models, AI inference, distributed AI systems, system design, performance optimization, latency reduction, throughput scaling, resource utilization, cost efficiency, KV cache management, intelligent routing, scheduling, distributed serving, heterogeneous inference, large-scale model parallelism
Preferred skills
Agentic AI, NVIDIA Dynamo, TensorRT-LLM, disaggregated serving, expert parallelism, cloud service provider infrastructure
Technologies
NVIDIA accelerated computing platforms, TensorRT-LLM, NVIDIA Dynamo
Responsibilities
Design and optimize large-scale LLM and Agentic AI inference systems; Analyze end-to-end inference workloads to improve latency, throughput, and cost efficiency; Develop solutions for emerging challenges like KV cache management and distributed serving; Build proof-of-concepts and reference solutions; Partner with Engineering, Product, Sales, and Business Development teams
Seniority
Senior, hands-on IC
