Hi, I'm Akash.
Applied AI & Software Engineer. A B.Tech graduate from IIT Roorkee. I build semantic search, AI personalization, LLM-driven workflows, and backend systems that hold up in production.
Open to AI and SDE roles
Things I've built
300ms Semantic Search on a Candidate Listing Page
Vector search over hundreds of thousands of candidates is fast, a steady 10 to 30ms. The latency that threatens a search page lives in everything around it. Here's how the whole path holds about 300ms at p95.
Building a Cost-Effective Vector Embedding Sync Pipeline for Semantic Search
The expensive part of a vector sync pipeline is almost never the embedding call. It's how often you make it, and how often you didn't need to.
Get in touch
If you're building something with RAG, LLM or agent-backed systems?
Want to argue about when a re-ranker actually earns its place in a search pipeline, I'd like to hear about it.