I design and build scalable, fault-tolerant distributed systems in cloud environments. I focus on solving complex backend problems, improving reliability, and driving engineering excellence.
Built a Slack-based AI assistant handling ~85% of support traffic across 220+ channels. Reduced support volume by ~27% using LLMs, RAG, and automation pipelines.
Led migration to a scalable system screening 130M+ users using Kafka, microservices, and AWS infrastructure.
Designed and optimized an AI pipeline generating 26,000+ structured review artifacts. Reduced runtime significantly and cut AI costs by up to 80%.