Skip to content
View AShirsat96's full-sized avatar
  • Singapore

Block or report AShirsat96

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
AShirsat96/README.md

Hi, I'm Aniket Shirsat πŸ‘‹

Python AWS Machine Learning Generative AI LangGraph

Data Scientist | AI Practitioner

I am a Singapore-based Data Scientist and AI Practitioner passionate about building intelligent AI systems that solve real-world business problems.

My work spans Generative AI, Agentic AI, Large Language Models (LLMs), Retrieval-Augmented Generation (RAG), Machine Learning, Cloud AI, Document Intelligence, Predictive Analytics, and Enterprise AI Applications.

I enjoy taking AI solutions from concept to deployment by combining data science, software engineering, and cloud technologies to build practical, production-ready AI systems.


About Me

  • πŸ‡ΈπŸ‡¬ Singapore Citizen
  • πŸŽ“ M.S. Applied Data Science, Indiana University Indianapolis (4.0/4.0 GPA)
  • πŸŽ“ M.S. Management (Finance), Singapore Management University
  • πŸ’Ό Data Scientist at Nautarex Systems
  • 🌱 Currently exploring Agentic AI, Enterprise AI, Multi-Agent Systems, and Production AI Applications
  • πŸ’¬ Interested in Applied AI, Machine Learning, Cloud AI, and Enterprise AI Solutions

Featured Projects

πŸ€– Multi-Agent Insurance System

Enterprise AI assistant built using LangGraph that coordinates multiple specialized AI agents for customer support, billing, payment history, policy information, and human escalation workflows.

Tech Stack

LangGraph β€’ OpenAI β€’ ChromaDB β€’ SQLite β€’ Agentic AI


πŸ“Š AI Business Analytics Assistant

Multi-agent AI system that converts natural language into SQL, executes database queries, generates business insights, and produces interactive Plotly visualizations.

Tech Stack

LangGraph β€’ Chainlit β€’ OpenAI β€’ SQLite β€’ Plotly


🩺 End-to-End Diabetes Risk Prediction System

End-to-end machine learning application using Apache Spark and AWS SageMaker Serverless to predict diabetes risk through an interactive Dash application.

Tech Stack

Python β€’ Apache Spark β€’ AWS SageMaker β€’ Dash β€’ Machine Learning


πŸ“„ Intelligent Document Processing

Cloud-based invoice processing pipeline using AWS Textract to automatically extract structured information from invoices and expense receipts.

Tech Stack

AWS Textract β€’ Python β€’ OCR β€’ Document AI


🎀 Speech Emotion Recognition with Wav2Vec2

Transformer-based Speech Emotion Recognition system using Wav2Vec2, Attentive Statistical Pooling, and Additive Margin Softmax for emotion classification.

Tech Stack

PyTorch β€’ Hugging Face Transformers β€’ Wav2Vec2 β€’ Audio AI


Technical Skills

Programming Languages

Python β€’ SQL β€’ R β€’ Flutter


AI & Generative AI

OpenAI API β€’ LangGraph β€’ LangChain β€’ LlamaIndex β€’ Ollama β€’ Prompt Engineering β€’ Agentic AI β€’ Retrieval-Augmented Generation (RAG)


Machine Learning & Deep Learning

PyTorch β€’ TensorFlow β€’ Scikit-learn β€’ XGBoost β€’ Hugging Face Transformers


Cloud & AI Platforms

AWS (Textract, SageMaker, Lambda, Rekognition, SES)

Google Cloud (Vertex AI, Gemini)

Microsoft Azure


Data Science & Visualization

Pandas β€’ NumPy β€’ Plotly β€’ Tableau β€’ Power BI


Current Interests

  • Agentic AI
  • Enterprise AI Systems
  • Large Language Models (LLMs)
  • Retrieval-Augmented Generation (RAG)
  • Multi-Agent Systems
  • Document Intelligence
  • Machine Learning
  • Cloud AI
  • AI for Business Applications

Featured Repositories

⭐ Multi-Agent Insurance System

⭐ AI Business Analytics Assistant

⭐ End-to-End Diabetes Risk Prediction System

⭐ AWS Textract Invoice Analyzer

⭐ Speech Emotion Recognition with Wav2Vec2


Connect with Me

🌐 Portfolio

https://aniketdshirsat.com

πŸ’Ό LinkedIn

https://www.linkedin.com/in/aniketshirsatsg/

πŸ“§ Email

aniketdshirsat@hotmail.com

Pinned Loading

  1. AWS_Textract_Analyze_Invoice AWS_Textract_Analyze_Invoice Public

    Automated invoice processing using AWS Textract to extract structured data from expense documents and receipts. Eliminates manual data entry for accounting departments, speeds up expense reporting …

    Jupyter Notebook

  2. Multi-Agent-Insurance-System Multi-Agent-Insurance-System Public

    Multi-agent AI insurance support assistant built with LangGraph, OpenAI, ChromaDB, and SQLite.

    Jupyter Notebook

  3. End-to-End-Diabetes-Risk-Prediction-System End-to-End-Diabetes-Risk-Prediction-System Public

    End-to-end diabetes risk prediction system using Apache Spark, AWS SageMaker Serverless, and Dash with a live deployed application.

    Jupyter Notebook

  4. AI-Business-Analytics-Assistant AI-Business-Analytics-Assistant Public

    Multi-agent AI system built with LangGraph, OpenAI, Chainlit, SQLite, and Plotly that converts natural language into SQL queries, executes them, and generates business insights with interactive vis…

    Jupyter Notebook

  5. Speech-Emotion-Recognition-with-Wav2Vec2 Speech-Emotion-Recognition-with-Wav2Vec2 Public

    Transformer-based Speech Emotion Recognition system using Wav2Vec2, Attentive Statistical Pooling, and Additive Margin Softmax for emotion classification on the IEMOCAP dataset.

    Jupyter Notebook