Skip to content
View JC230903's full-sized avatar
🎯
Focusing
🎯
Focusing

Block or report JC230903

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Maximum 250 characters. Please don’t include any personal information such as legal names or email addresses. Markdown is supported. This note will only be visible to you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
JC230903/README.md

Hi 👋, I'm Jacob Cherian

Backend Engineer • AI Builder • Data & Research Enthusiast

Profile Views


👨‍💻 About Me

I'm a Computer Science graduate interested in backend engineering, applied AI, data engineering, and research-driven software development.

I enjoy building systems end to end — from designing APIs and databases to developing retrieval pipelines, data workflows, and AI-powered applications.

My recent work has involved:

  • Backend development with Python, FastAPI, PostgreSQL, and REST APIs
  • AI systems using RAG, LangChain, LangGraph, LLMs, and multi-agent workflows
  • Data engineering with PySpark, Databricks, Delta Lake, and ETL pipelines
  • Research involving computer vision, OCR, NLP, and low-resource languages
  • Algorithmic problem solving with 750+ LeetCode problems

I'm particularly interested in understanding how systems work under the hood and continuously improving their performance, reliability, scalability, and maintainability.


🚀 What I Work On


🛠️ Tech Stack

Languages

Backend & Databases

AI / Data / Cloud

AI: RAG • LangChain • LangGraph • LLM Workflows • Multi-Agent Systems • Mistral 7B

Data: PySpark • Databricks • Delta Lake • ETL • Big Data Analytics

Tools: Git • GitHub • VS Code • Jupyter • Postman


🚀 Featured Projects

🤖 Agentic RAG System

Built a document-based question answering platform using FastAPI, LangChain, FAISS, and Mistral 7B.

  • Designed semantic document retrieval and context-aware generation
  • Improved answer quality through chunking and prompt optimization
  • Focused on grounded responses and citation reliability
  • Explored latency and retrieval-quality tradeoffs
  • Built around a real-world client-facing use case

⚡ FastAPI + PostgreSQL Backend

Built a modular backend service for a social media application.

  • JWT-based authentication
  • RESTful CRUD APIs
  • PostgreSQL database integration
  • Voting and post interaction logic
  • API testing using Postman
  • Modular backend architecture

📊 Databricks Data Engineering Pipeline

Built an ETL pipeline for Apple product sales analysis using Spark and PySpark.

  • Processed CSV and Parquet datasets
  • Used Delta tables for structured data storage
  • Implemented transformation pipelines with PySpark
  • Applied Spark SQL for analytical workloads
  • Designed the workflow around scalable data processing

🍽️ MERN Restaurant Management System

Developed a full-stack restaurant management platform using the MERN stack.

  • Menu management
  • Order management
  • Table reservations
  • Operational dashboard
  • REST API integration
  • Frontend-backend integration

🔬 Research & Open Source

📄 Low-Resource Language Processing

Co-authored research on:

"Low-Resource Language Processing: An OCR-Driven Summarization and Translation Pipeline"

The work combines:

OCR → NLP → Summarization → Translation

with a focus on processing low-resource Indian languages.


🧠 Computer Vision Research

Worked on AI and computer vision projects involving YOLO-based object detection and image processing, exploring practical applications of deep learning.


🌱 Open Source

Explored open-source development through Google Summer of Code and contributed to work around PyBaMM, including efforts related to improving type support within the project.


🏆 Highlights

Achievement Details
💻 Competitive Programming 750+ LeetCode Problems
🏅 LeetCode Knight • Top 5%
☁️ Cloud AWS Certified Cloud Practitioner
🐍 Python PCAP – Certified Associate Python Programmer
🤖 AI Azure AI Fundamentals
📊 Data Google Advanced Data Analytics
🔬 Research Published research in AI / NLP
🌱 Open Source Google Summer of Code experience


📜 Certifications

  • AWS Certified Cloud Practitioner
  • PCAP — Certified Associate Python Programmer
  • Microsoft Azure AI Fundamentals
  • Google Advanced Data Analytics
  • Google Data Analytics
  • IBM AI Developer
  • Meta Back-End Developer
  • Machine Learning — University of Washington

📈 GitHub Activity

GitHub Stats

Top Languages

GitHub Activity Graph


📚 Currently Learning

System Design
      ↓
Scalable Backend Architecture
      ↓
Distributed Systems
      ↓
LLM / Agentic Systems
      ↓
Production AI Engineering

I'm particularly interested in the intersection of backend engineering and AI infrastructure — building reliable systems rather than isolated AI demos.


🤝 Let's Connect


Building systems, solving problems, and learning one commit at a time.

Popular repositories Loading

  1. Face_recognition_project Face_recognition_project Public

    Face_recognition project in python using multiple python libraries creating an AI/ML project

    Python 1

  2. PageGenie PageGenie Public

    An AI-powered application that transforms standard PDFs into beautifully illustrated digital books with thematic marginalia generated from the text.

    Python 1

  3. Python_project Python_project Public

    python-project for semester-4

    Python 1

  4. MusicPlayer MusicPlayer Public

    Forked from rajaprerak/MusicPlayer

    Music Player with Django. Simple and easy to use music streaming website.

    HTML

  5. vibescape vibescape Public

    Forked from NebulaTris/vibescape

    Emotion based music recommender system

    Python 1

  6. AI-Expert-Roadmap AI-Expert-Roadmap Public

    Forked from AMAI-GmbH/AI-Expert-Roadmap

    Roadmap to becoming an Artificial Intelligence Expert in 2022

    JavaScript