Exploring production data systems, applied AI, and the craft of building reliable ML infrastructure at scale.
Key learnings from deploying a customer-facing RAG system at scale, including techniques for reducing hallucinations and improving retrieval quality.
Practical strategies for improving query performance in AWS Athena, from partitioning strategies to query restructuring.
Experiences from C-DAC on managing distributed NWChem workloads and preparing outputs for downstream ML models.
Subscribe to receive technical articles and project updates directly to your inbox.
Newsletter coming soon. For now, connect with me on LinkedIn.
Vaibhav's AI Assistant