Skip to content
View karthik-k11's full-sized avatar
:octocat:
Building AI Agents
:octocat:
Building AI Agents

Block or report karthik-k11

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
karthik-k11/README.md

Karthik K

Data Scientist

🌐 Portfolio


πŸ™‹β€β™‚οΈ About Me:

  • πŸ§‘β€πŸ’» Currently working as a Data scientist and AI/ML Intern at Analogica Software Development, Bengaluru.
  • πŸ“š Pursuing MCA with a strong focus on Artificial Intelligence and Data Science.
  • βš™οΈ Exploring areas like Generative AI (LLMs), RAG Systems, Multi-Agent Architectures, and Computer Vision.
  • 🧠 Passionate about building intelligent AI agents, automating workflows, and solving real-world problems with AI.
  • 🀝 Open to collaborating on Generative AI, RAG Pipelines, Agentic Workflows, and End-to-End ML projects.
  • πŸ“« Reach me at: karthikk1162@gmail.com

πŸš€ Languages and Tools:







πŸ€– Project

🧠 RAG Knowledge Engine

A Retrieval-Augmented Generation (RAG) system engineered to provide accurate, source-backed answers from custom datasets.

Key Technical Implementations:

  • LangChain Orchestration: Utilized the LangChain framework to construct a robust retrieval pipeline connecting Google Gemini 1.5 Flash with custom data sources.
  • Vector Retrieval System: Integrated ChromaDB (Vector Store) and HuggingFace Embeddings to enable high-precision search based on document meaning.
  • Explainable AI: Developed a transparent citation mechanism that tracks and displays the exact source document and page number for every answer.
  • Secure Data Handling: Implemented ephemeral (temporary) file processing logic to ensure user data privacy during document ingestion.

✍️ Article

"I still remember the excitement of seeing my first machine learning model display perfect accuracy... But reality struck when I tested the model on unseen examples."

In this article, I explore the Bias-Variance Tradeoff, break down Regularization techniques (Lasso, Ridge, Elastic Net), and share strategies to build models that generalize to real-world data.


πŸ“œ Certifications

  • Data Science with Python – Certisured (March 2025)
  • Machine Learning – IBM
  • Java Programming (12 Weeks) – NPTEL
  • Data Analytics and Visualization – Accenture

πŸ’‘ β€œWhat we want is a machine that can learn from experience.”
β€” Alan Turing

Pinned Loading

  1. Machine-Learning Machine-Learning Public

    This repository contains various Machine Learning models and experiments implemented in Python using Jupyter Notebooks (.ipynb). The aim is to explore, understand, and apply different ML algorithms…

    Jupyter Notebook 1

  2. Deep-Learning Deep-Learning Public

    A repository documenting my journey as I learn and implement deep learning models using Tensorflow and Keras

    Jupyter Notebook 1

  3. Data-Science-Libraries-Practice Data-Science-Libraries-Practice Public

    Practice and experimentsnwith core python Data Science libraries like pandas, numpy, Matplotlib and seaborn

    Jupyter Notebook 1

  4. civic-helper-agent civic-helper-agent Public

    A Multi-Agent AI Framework for Automated Issue Reporting, Formal Letter Generation, and Department-Level Routing

    Jupyter Notebook 2