Skip to content
View yohanmarkose's full-sized avatar

Block or report yohanmarkose

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 supported. This note will be visible to only you.
Report abuse

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

Report abuse
yohanmarkose/README.md

Hi there, I'm Yohan Markose! 👋

LinkedIn Portfolio Email

🚀 About Me

I'm a Data Science & AI enthusiast pursuing my MS in Information Systems at Northeastern University (GPA: 4.0). With nearly 3 years of experience in Data Analysis and automation in the pharmaceutical industry, I've helped leading companies like Novartis and Pfizer transform their data operations through automation and intelligent analytics.

Currently based in Boston, MA | Open to opportunities nationwide


🔭 What I'm Currently Working On

  • Agentic RAG Pipeline: Multi-agent Agentic RAG system using multiple MCP server and a complete data pipleine with orchestration
  • ML-Ops: building a Complete ML-Ops pipleine from data preperation -> fine tuning a model -> deployment -> Monitoring

🌱 Currently Learning & Exploring

  • Advanced LLM Integration and Agentic AI Systems
  • Deep Learning for predictive modeling and fine tuning
  • MLOps best practices for production-ready ML systems

👯 Looking to Collaborate On

  • Data Science Projects in healthcare, finance, or tech
  • AI/ML Applications for business process optimization
  • Open Source Contributions in data engineering and analytics
  • Automation Solutions that drive operational efficiency

🛠️ Technical Arsenal

Languages & Core Technologies

Python SQL Java C++ HTML5 CSS3

Data Engineering & Cloud

Apache Airflow Docker Snowflake dbt AWS Google Cloud

AI/ML & Data Science

TensorFlow scikit-learn Pandas NumPy Matplotlib Plotly FastAPI LangChain MCP


"Transforming data into insights, automation into efficiency, and ideas into impact."

Pinned Loading

  1. Electric_Car_Emission_impact--Baysian_Statistics Electric_Car_Emission_impact--Baysian_Statistics Public

    A repository containing the All the data science projects I have done

    Jupyter Notebook

  2. FRED_Snowflake-Pipelines FRED_Snowflake-Pipelines Public

    Jupyter Notebook

  3. RAG_Flex RAG_Flex Public

    The project develops an AI system to automate the retrieval and analysis of NVIDIA’s financial reports, using Apache Airflow and a Streamlit interface for data exploration and custom document uploads.

    Jupyter Notebook

  4. SEC-Bridge SEC-Bridge Public

    SECBridge is a high-performance financial data pipeline that automates the extraction, transformation, validation, and visualization of SEC financial statement data. Built with Snowflake, Apache Ai…

    Jupyter Notebook

  5. Venture-Scope Venture-Scope Public

    Venture Scope is an AI-powered advisory platform that transforms complex market data into clear, actionable insights. We help entrepreneurs make informed decisions by analyzing location dynamics, c…

    Jupyter Notebook

  6. Web-and-PDF-Data-Extraction-App Web-and-PDF-Data-Extraction-App Public

    A Streamlit-based app with a FastAPI backend for extracting structured data (text, images, tables) from websites and PDFs. Processed data is stored in AWS S3 and rendered in a markdown-standardized…

    Jupyter Notebook