Easily productionize open source models with one-click Hugging Face imports. Learn how Snowflake’s vLLM architecture optimizes memory for maximum throughput.
APR 17, 2026|6 min read
Sasank Chindirala
Sasank Chindirala is a Software Engineer on the Model Serving team at Snowflake, working at the forefront of Large Language Model inference and AI Agent infrastructure. He plays a key role in building and hardening the platform's model serving capabilities, from integrating new inference engine backends and designing inference protocols, to simplifying the end-to-end model usage experience. His work spans the full lifecycle of model deployment, encompassing model registry, and inference serving across a wide range of AI workloads - from classical ML frameworks to LLMs and Agents. Outside of work, you'll find him at the gym or geeking out over research in math and AI.
