Blog

The infrastructure half of GenAI: prefill vs. decode, why the KV cache is your real constraint, continuous batching, quantization trade-offs, and how to plan capacity without guessing.

How to take an LLM feature from a notebook demo to something a team can change safely — eval sets built from real traffic, honest grading methods, CI regression gates, and production tracing.

The engineering reality of LLM agents — the loop, tool design, planning strategies, memory, and the guardrails that keep long runs from spiraling. Plus an honest look at when a plain pipeline beats an agent entirely.

What actually breaks when you take a RAG prototype to real users — chunking, hybrid retrieval, reranking, context assembly, and index operations — plus how to tell a retrieval failure from a generation failure.

A practical guide to system design fundamentals — from scalability and load balancing to database choices, caching strategies, and real-world architecture patterns that power modern applications.

What IaC is, why Terraform, how state, modules, and environments fit together—with pragmatic patterns you can use today.

A hands-on guide to Docker for developers: advanced patterns, real-world Dockerfiles, multi-stage builds, debugging, and performance tips. Includes code, tables, and practical advice.

Level up your TypeScript skills with these practical tips and code snippets for safer, cleaner, and more productive code.

Introduction to my journey as a Full Stack Engineer and the projects I'm passionate about.