Experienced Data Engineer with a proven track record of about 2.5 years in the field. Specializing in Data Science Techniques, I excel in end-to-end ML model building, chatbots development, and leveraging GPT projects for generative AI solutions. Passionate about harnessing data to drive innovation and enhance user experiences.
Overview
3
3
years of professional experience
1
1
Certification
Work History
Data Engineer
iLearning Engines India Private Limited
06.2022 - Current
AI Worker creation using Django, LLM, Kubernates
Orchestrated the development of an assessment generation feature within LMS platforms, enhancing user engagement and streamlining processes. Leveraged advanced prompt engineering techniques on OpenAI to optimize model performance, ensuring accurate and efficient responses. Proficiently integrated diverse technologies, including PostgreSQL for collaborative database management, to create seamless and impactful solutions, resulting in improved functionality and user satisfaction
Developed a versatile dashboard application using Python with Streamlit and Dash, featuring a variety of charts and plots created using Matplotlib, Seaborn and Plotly libraries. Integrated this dashboard with an existing React application, connecting the backend functionalities via FastAPI for seamless user interaction and real-time data insights
Created a Python program using PyPDF2 and doc2txt libraries to extract headings and paragraphs from both documents and URLs
This tool simplifies the process of gathering structured text content from various sources, making document analysis and processing easier and more efficient
Improved an Invoice Processing App (FinApp) powered by AWS Textract by adding a solid business validation feature. Used MongoDB to get and analyze data for validation. Made sure to handle errors gracefully, closing any potential loopholes in the code. The upgrade ensures the app runs smoothly, meeting business needs accurately
Created a chatbot using Rasa framework, mastering intents and stories for better understanding. Added a feature to connect with OpenAI's ChatGPT for answering unique questions. Also, integrated an existing chatbot API to expand capabilities. These improvements make the chatbot smarter and more helpful to users
Enhanced understanding of Power BI dashboard creation specifically for insurance data, including report generation and data manipulation tailored to insurance industry needs
Data Scientist - Intern
First Principal Labs
03.2022 - 05.2022
Built out the data and reporting infrastructure from the ground up using SQL and Tableau to provide real-time insight
Implemented Web scrapping using beautiful soup and selenium
Built gold price prediction modal using decision tree regressor as benchmark modal and solution random forest as solution modal
Built fake review detection model using Sentiment analysis and classification algorithms like SVM and KNN, SVM overperforms KNN with 75% accuracy
Developed a text summarization modal using NLP
Analyzed plug-in dataset to predict the installation growth using the LSTM time series algorithm
Performed Sentiment analysis on review dataset using various models like Roberta, Vadar, and Text blob
Built a modal to predict customer churn rate using ensemble techniques
Analyzed Market Basket Analysis using unsupervised machine learning algorithms like apriori algorithm
Experience in data visualization packages like seaborn and matplotlib
Built knowledge graph of review dataset using genism and spacy library
Developed a hyper-tuning script for a neural network that detects human emotion
Education
Post Graduate Diploma - Data Science and Analytics
Kannur University
India
01-2022
Master of Arts - Economics
Central University of Kerala
India
01-2021
Skills
Language
Python
Framework
Rasa
FastAPI
Django
IDE
PyCharm
VS Code
VIM
Data Science Techniques
Machine Learning
Deep learning
Natural Language Processing
Regression
Classification
Clustering
Decision tree
Neural network
Data visualization
Data Modeling
(Familiar with Scikit-learn, PyTorch, TensorFlow, Bert, Keras LLM, Open AI, Lang chain, NumPy, SciPy, Pandas, Spacy)
Database
MongoDB
MySQL
Milvus
Qdrant
Chroma DB
Data Analysis-Reporting & Dashboard Framework
Streamlit
Dash
Power BI
Tableau
Others
MS Office
Postman
Data warehouse management
Docker
AWS S3
Apache Superset
Apache Airflow
Risk Analysis
Languages
Professional working proficiency in English
Native proficiency in Malayalam
Limited working proficiency in Tamil, Kannada & Hindi
Certification
IBM Applied AI Specialization Course provided by IBM and Professional certificate issued by Coursera Including six course certificates
Profit Analysis Using Economic Value-Added A non-credit project authorized and offered by Coursera
Chatbot Building Essentials Badge issued by IBM Developers Skills Network powered by Coursera
(Analytics on SAS, Statistics for Data Science, Python for Machine Learning, Data Visualization using Tableau, Data Visualization with Power BI - Courses provided by GL Academy )
Timeline
Data Engineer
iLearning Engines India Private Limited
06.2022 - Current
Data Scientist - Intern
First Principal Labs
03.2022 - 05.2022
Post Graduate Diploma - Data Science and Analytics
National Sales Head at Vedhik IAS Academy & Vedhik Ai Schools -iLearning EnginesNational Sales Head at Vedhik IAS Academy & Vedhik Ai Schools -iLearning Engines