AI Data Engineer and MLOps Engineer with experience building productiongrade data and AI systems across Azure, AWS, GCP, and Databricks. I develop ETL pipelines, cloud-based data workflows, and CI/CD processes that support analytics, machine learning, and regulated business use cases. My background combines Python, SQL, JavaScript, and modern MLOps practices with hands-on delivery of scalable data platforms, model deployment, and automation. I work comfortably across data engineering and AI teams, translating technical requirements into reliable solutions with strong attention to data quality, governance, and operational performance.

• Porfolio website

• AI & Machine Learning: Python, TensorFlow, Keras, PyTorch, scikit-learn, CNNs, Transformers,Glue
• NLP & CV: LangChain, LangGraph, Hugging Face Transformers, OpenAI API, RAG, OpenCV
• Cloud & DevOps: AWS, GCP, Azure, Docker, Kubernetes, CI/CD, Databricks
• Web & Full-Stack: React, Flask, Django, HTML/CSS, JavaScript
• Databases: MySQL, PostgreSQL, MongoDB, SQLite

Here are a few projects you can find on my GitHub:

• 🧠 TracerLensAi: TracerLensAi is a cloud-native AI chat interface powered by Google Gemini. It provides an interactive workspace for evaluating agentic workflows with causal reasoning, live code execution, and web search — all backed by a production-grade GCP deployment pipeline.

• 🛠️🔄 End-to-end MLOps with Databricks: This repository provides a simple, end-to-end MLOps architecture implemented within the Databricks platform. It includes a minimal, working machine learning project that demonstrates the key stages of an MLOps lifecycle, including data preparation, model training and tracking (using MLflow), model registration, and batch inference or serving.

• 🌿🔬 CNN for Plant Disease Classification: A production-ready MLOps system for classifying plant diseases (Healthy, Powdery, Rust) using Convolutional Neural Networks (CNNs). This project transforms a research notebook into a scalable, reproducible, and automated machine learning pipeline.

• 🍄💻 Mushroom Classification Analysis: 🍄Mushroom Classification with MLOps. This repository contains a complete Python solution for classifying mushrooms as edible or poisonous using various Machine Learning algorithms. More importantly, it demonstrates how to transform an experimental ML model into a reliable, production-ready system through the adoption of MLOps principles.

• 🕸️ Knowledge Graph RAG System: Implementation of a GraphRAG system using a Flask application with the Ollama API and locally built models, leveraging graph-based structures for advanced query retrieval.

• 💬🤖 Context-Aware Chatbot Using RAG Framework: A context-aware chatbot built using a Retrieval-Augmented Generation (RAG) framework, leveraging state-of-the-art large language models such as OpenAI’s GPT and Meta’s Llama

• 📊 Twitter Sentiment Analysis for Financial Markets: A production-ready Flask application that analyses real-time tweets from top financial influencers and institutions using advanced NLP sentiment analysis. Track market sentiment, identify trends, and visualize financial opinions with an interactive dashboard.

• LinkedIn: linkedin.com/in/jacob-binu-4a0596205
• Email: jacobbinu4488car@gmail.com