About Me
My background, engineering philosophy, and the journey from AI Application Engineer to AI Agent / Runtime Engineer.
AI Agents
Agent architecture, LangGraph workflows, multi-agent orchestration, and tool-use patterns.
RAG Engineering
End-to-end retrieval-augmented generation: embeddings, vector search, reranking, and advanced patterns.
LLM Infrastructure
Deploying and serving LLMs at scale: inference optimization, SaaS architecture, and multi-tenant design.
Multimodal AI
ASR, TTS, vision-language models, and building systems that combine multiple modalities.
Projects
Real projects showcasing end-to-end AI system design and implementation.
What You’ll Find Here
This portfolio is organized as a technical reference for AI engineers, backend engineers, and developers building with LLMs. Each section combines conceptual explanations with working code examples drawn from real systems.Architecture Patterns
Reusable designs for agents, RAG, and LLM services — with diagrams and trade-off analysis.
Code Examples
Practical Python and TypeScript snippets you can copy-paste into your own projects.
Engineering Notes
Honest write-ups of what worked, what didn’t, and what I’d do differently.
This site is continuously updated as I build new systems and deepen my understanding of AI engineering. Check the Engineering Notes section for the latest lessons learned.
Quick Navigation
LangGraph Workflows
Design and implement stateful agent workflows using LangGraph’s graph-based primitives.
Embeddings & Vector Search
Choose embedding models, configure vector stores, and optimize retrieval quality.
LLM Deployment
Serve open-source and proprietary LLMs efficiently with vLLM, Ollama, and cloud APIs.
ASR & TTS Systems
Integrate speech recognition and synthesis into AI applications and voice agents.