Production Systems

Shipped AI systems: problem, approach, tech stack, and architecture.

Agentic Social Media Post Studio with MCP

If unavailable, the Azure VM may be stopped. Please contact me for a live demo.

Problem — Creating high-quality, on-brand LinkedIn posts from PDFs, URLs, and images required coordinated planning, research, copywriting, visual generation, and review workflows—not a single prompt.

Engineering Challenge — Built a multi-agent orchestration system with explicit agent roles, critic-feedback loops, MCP-powered tool access, and multimodal RAG while maintaining traceability, partial reruns, and debuggable execution flows.

Tech Stack — LangGraph, MCP, ChromaDB, OpenAI, LangSmith, Docker, Streamlit

Architecture —

User Input (PDF / URL / Image) ↓ Streamlit UI ↓ LangGraph Workflow ↓ MCP Tools + ChromaDB RAG ↓ Final LinkedIn Post + Assets

Deployment — Containerized and deployed on an Azure VM using Docker and Docker Compose. The Streamlit app and MCP server run as separate services with shared persistent storage, environment-based configuration, and port exposure for the public live demo.

RAG-Powered Knowledge Base

Problem — Teams needed accurate, cited answers from internal docs without hallucination.

Engineering Challenge — Balancing retrieval quality, context length, and latency for real-time chat.

Tech Stack — LLM, BGE-M3, Qdrant, LangChain, FastAPI

Architecture —

User query → embedding → vector search (Qdrant) → top-k retrieval → LLM prompt with context → streamed response.

AI Chat for Portfolio

Problem — Visitors wanted to ask questions about my work and get accurate, contextual answers.

Engineering Challenge — Building a small, reliable RAG pipeline with minimal infra and clear observability.

Tech Stack — Next.js, Django REST, OpenAI / Llama, Qdrant, PostgreSQL

Architecture —

Next.js frontend → Django API → embedding + vector search → LLM → response. Optional caching and rate limiting.

Document Classification Pipeline

Problem — Large volumes of documents needed consistent tagging and routing for downstream workflows.

Engineering Challenge — Throughput, cost control, and handling edge cases without manual review.

Tech Stack — Python, Transformers, Celery, PostgreSQL, S3

Architecture —

Ingest → queue (Celery) → embedding + classifier → write labels and metadata → trigger workflows.

Try AI Demo