About
Vaibhav Agarwal is an engineer who builds AI products end to end — from the LLM pipeline down to the infrastructure that keeps it running.
His work lives where AI meets real systems: retrieval, agents, evaluation, and backend plumbing. He studied electrical engineering at IIT Kanpur and is completing a master's in AI at Georgia Tech.
Along the way he has founded companies, angel-invested, and shipped AI systems in production — most recently GEO work at Siftly (opens in a new tab) (YC), and now AI development at Monaco (opens in a new tab).
- Now Building at Monaco (opens in a new tab) (AI CRM)
- Before Siftly (opens in a new tab) (YC)
- MS AI Georgia Tech
- BTech EE IIT Kanpur
Focus areas
Retrieval & RAG
Chunking, embeddings, hybrid search, reranking — and measuring whether any of it actually helps.
Agents
Agents that don't fall over: evals, harnesses, guardrails, and tools an LLM won't misuse.
Evaluation
Retrieval metrics, eval harnesses, and catching quality regressions before users do.
Distributed systems
Event-driven architectures, queues, consistency, and failure handling — what decides whether a system survives real traffic.
Backend engineering
APIs, data models, Postgres, and services that are boring in the best way: observable, testable, and fast.
Infrastructure
Caching, rate limiting, streaming, deployment, and cost — the plumbing that keeps LLM systems reliable and affordable.
Get in touch
The fastest way to reach me is email: vaibhavkumaragarwal2020@gmail.com. I'm also on LinkedIn (opens in a new tab), X (opens in a new tab), GitHub (opens in a new tab) and Instagram (opens in a new tab).