Design and build agentic AI systems that generate, analyze, and optimize GPU compute kernels
Collaborate with GPU architects and performance engineers to encode domain expertise
Build automated performance forensics agents capable of ingesting large-scale simulation traces
Partner with HW architects to develop agentic flows for GPU architectural studies
Explore agentic approaches to HW/SW co-design challenges
Rapidly prototype and thoughtfully productize
Set up evaluation backbone using offline golden sets and online telemetry
Mentor and improve teams through insights in agent orchestration

8+ years in applied ML/AI or large-scale systems
2+ years crafting agentic or LLM-powered applications in production environments
B.Sc in Computer Science / Electrical Engineering
Solid grounding in computer architecture: memory hierarchies, parallelism models, pipelining, and cache behavior
Familiarity with NVIDIA GPU architecture: streaming multiprocessors, warp scheduling, shared/global memory model, and occupancy reasoning
Hands-on CUDA programming experience: writing, profiling, and optimizing GPU kernels
Comfortable with tools such as Nsight Compute, Nsight Systems, or equivalent profiling workflows
Proven ownership of at least one end-to-end agentic system or LLM application
Strong software engineering skills in Python and one systems language (C++ preferred)
Proficient in tool use, RAG pipelines, and model adaptation techniques for building agentic systems
Demonstrated ability to collaborate with HW/SW domain experts
Excellence in communication and facilitation
Track record of building observability for AI systems

Senior LLM Agents Architect

Key skills