I’m Aniketh — 12 years as a backend engineer, most recently building large-scale distributed systems and observability infrastructure.

I’m now focused on AI engineering: production LLM systems, RAG, agents, evals, and the serving/infra layer that makes a model reliable and cost-controlled at scale.

I write about what I build here — RAG pipelines, agent architectures, fine-tuning, vLLM serving, ML platform infra — with real numbers and real failures, not demos.