Skip to content
View ak7599's full-sized avatar
3 followers · 7 following
  • pune

Block or report ak7599

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
ak7599/README.md

👋 Hi, I'm Ajay Radhakishan Kalaskar

Data Scientist | AI Engineer | Spectroscopy & Signal Processing Specialist

I’m a Data Scientist with 3+ years of experience building Machine Learning models, Generative AI workflows, Raman Spectroscopy analytics, calibration pipelines, and backend automation systems.

My work lies at the intersection of ML, signal processing, physics-based modeling, and device-level automation. I love solving analytical problems using a mix of domain knowledge + algorithms + experimentation.

🔬 What I Work On

  • 🧪 Raman Spectroscopy Analytics
    Peak detection, baseline correction, quantification, mixture analysis, calibration algorithms
  • 🤖 Machine Learning & Deep Learning
    Classification, clustering, PCA, SVM, Random Forest, CNNs
  • 🧠 GenAI & LLMs
    RAG, LangChain, FAISS, Embeddings, Gemini 1.5 Pro
  • ⚙️ Backend Automation
    Python APIs, ETL workflows, data validation, reporting engines
  • 🧰 Research Paper Implementations
    Converting academic algorithms into production-ready code

🛠️ Tech Stack

Languages: Python, SQL
ML Libraries: TensorFlow, Scikit-learn, SciPy, NumPy, Pandas
Visualization: Matplotlib, Plotly, Tableau
GenAI Tools: LangChain, FAISS, Embedding Models
Dev Tools: Git, VS Code, Jupyter, GCP
Other: Automation scripts, calibration modules, ETL pipelines

🚀 Featured Work

🔹 Spectral Analysis Engine

Backend for Raman preprocessing, calibration, peak extraction & quantification.

🔹 Expert Review System

Automated manual-review workflow for ambiguous cases, reducing workload by 40%.

🔹 RAG-based GenAI Assistant

LLM-powered internal assistant using LangChain + FAISS + Gemini 1.5 Pro.

🔹 Optical Module Automation

Automated device-level scan processing & calibration workflows.

📚 Current Focus

  • Improving spectral ML models using physics-informed features
  • Building reliable calibration and drift-correction algorithms
  • Experimenting with LLM-based automation & RAG workflows
  • Contributing to open-source ML and signal processing tools

📫 Let's Connect

💼 LinkedIn: linkedin.com/in/ajay-kalaskar-a9781b178
📧 Email: ajay.kalaskar99@gmail.com

⭐ If you like my work, consider giving a star to the repositories you find useful!

Popular repositories Loading

  1. IBM_coursera_ML_best_classifier IBM_coursera_ML_best_classifier Public

    Jupyter Notebook 1

  2. EDA_911_emergency_calls EDA_911_emergency_calls Public

    911 is a North American emergency helpline number . By doing analysis of this dataset we will try to understand whether emergency response team is well equipped to deal with emergencies or not.We w…

    Jupyter Notebook 1

  3. EDA_stok_prices_Banks EDA_stok_prices_Banks Public

    In this project we will focus on EDA( Exploratory data analysis) of stock prices of 6 major banks from the world. We will focus on the bank stocks and see how they are progress through the financia…

    Jupyter Notebook 1

  4. Linear-Regression Linear-Regression Public

    In this we use liner, multiple, polynomial algorithms

    Jupyter Notebook

  5. Logistic_Regression Logistic_Regression Public

    In Logistic Regression algorithm, making prediction on classification data like (merge) churn_data.csv,internet_data.csv,customer_data.csv

    Jupyter Notebook

  6. K_Nearest_Neighbours-KNN- K_Nearest_Neighbours-KNN- Public

    KNN is classification algorithm in which nearest data points are considered for prediction of testing data points. In this algorithm we worked on gene_expression.csv dataset.

    Jupyter Notebook