Bio
Tanay Varshney is a principal engineer at NVIDIA working on NeMotron models, NeMo Platform and LLM inference architecture at NVIDIA.
Sessions (2)
Additional Speaker Details
Using publicly available information we constructed an analysis to help you get a feel for this speaker before deciding to attend their session.
Tanay Varshney is an NVIDIA engineer who authors the developer-blog 'Easy Introduction' series on production LLM pipelines — covering RAG, multi-agent systems, LLM reasoning and test-time scaling, and inference optimization built on NVIDIA NIM and NeMo. In March 2025 he co-presented a GTC panel with Chip Huyen and Eugene Yan on hard-won lessons from shipping LLM applications. His writing stays accessible to newcomers while grounded in enterprise-scale deployment, making his session a fit for hands-on practitioners who want a guided tour of NVIDIA's agent and retrieval toolchain.
Speaking style
GitHub
@tanayvarshneyRecent writing (1)
- An Easy Introduction to LLM Reasoning, AI Agents, and Test Time Scaling · blog · May 2025