AI Engineer & Systems Architect
Builder. I use AI for impact, Data for intelligence, and Software Engineering for accessibility. Specialized in shipping production ready AI products from Multi-Agent Systems to LLM-powered assistants. I turn complex tech into elegant solutions that scale.
Attention Weights & Core Expertise
Attention(Q,K,V) = softmax(QKᵀ / √d_k)V — Continuous parameterization of AI and Systems Engineering capabilities.
Python
LangGraph&LangChain
JS & TS
FastApi
AWS
DSpy
OpenAI SDK
OpenAI, Groq, Anthropic, Gemini API's
Pytorch
Transformers
Baml & Flower
HuggingFace
Celery
LangSmith
MLFlow
Grafana&Prometheus
Docker
Git&GitHub
Numpy&Pandas
Tableau&PowerBi
Postgres
Supabase
Oracle
ReactJs
Scikit-learn
RAG
MCP
Linux
CrewAI
Research, Articles & Latent Thoughts
Vectorized technical writing exploring Deep Learning architectures, LangGraph multi-agent systems, and production AI.
Tools - The Hands of AI
Context Engineering: The Invisible Skill That Determines Whether Your AI Agents Actually Work
The one skill that separates production-grade AI agents from expensive hallucinations.
AI Workflows vs Agents: A Developer's Guide to Architectural Decisions
Integrating MCP Into Your Product: Why Your SaaS Needs Tool-Calling AI
In Part 1, we understood why MCP matters. In Part 2, we built a universal MCP client. In Part 3, we created the agentic layer. Now let's talk about why this matters for your product — and how to actually integrate it.test
Production Shipped Artifacts
Real-world end-to-end artificial intelligence platforms, LLM agents, and full-stack software deployed to production.
FlowSight
FlowSight is a local VS Code extension that provides "X-Ray vision" for your LangChain and LangGraph agents. It visualizes traces, metadata, and execution graphs in real-time, right next to your code.
mcp_client
A modern chat application that integrates the Model Context Protocol (MCP) to enable LLMs (Large Language Models) to use external tools in real-time.
Cursor clone
cursor clone (in progress)
angelAI
Chatbot that can answer questions from business angels about a company called Mistral AI.
postgres_with_bash
This project contains two separate subprojects, each using Bash scripts to interact with PostgreSQL databases. The first subproject, [students_database](./students_database), manages student and course data. The second subproject, [game_database](./game_database), manages World Cup match data.
AI Diagnosis with Crew AI
This project is a medical diagnosis application using artificial intelligence (AI). The application consists of two main parts: a frontend developed in Angular and a backend developed in Python. The backend uses Crew AI for patient diagnosis via a POST API with Flask. The frontend uses this API to submit patient information.
Initialize Inference & Contact
Ready to deploy cutting-edge AI architectures, agentic systems, or scale production machine learning pipelines?