ML Engineer with less than a year in AI, Data Science & Predictive Modeling
AI is analyzing your overall score…
Identifying your key strengths…
Evaluating your skill match against the job requirements…
Assessing your cultural and operational fit
Data Science graduate with strong foundations in Python, SQL, and statistics experienced in machine learning, predictive modeling, deep learning, and generative Al through hands-on internships and end-to-end project delivery. Built a binary classification model on 41,000+ customer records achieving 90.5% accuracy using XGBoost, developed electricity demand forecasting (MAE: 1.02 kWh, WAPE: 8.5%), and implemented RAG-based LLM pipelines for medical assistance. Proficient in EDA, ETL, feature engineering, model evaluation, and data visualization using Power BI and Tableau. Oracle Cloud Infrastructure 2025 Certified Data Science Professional. Seeking roles in Data Analytics, Machine Learning, Operational Analytics, and Risk Analysis.
PIET, Kurukshetra University
B.Tech Cse · Artificial Intelligence and Data Science
August 1, 2022 – June 30, 2026
JP DAV Public School
Secondary Education (XII)
June 1, 2022 – May 31, 2022
Raunaq Public School
Matriculation (X)
June 1, 2020 – May 31, 2020
Techgyan Technologies
Machine Learning Intern
July 1, 2024 – August 31, 2024
India
Teachnook
Data Science Intern
February 1, 2024 – March 31, 2024
India
24-Hour Electricity Demand Forecasting
June 1, 2026 – Present
Developed a 24-hour electricity demand forecasting model using Ridge Regression on smart meter data performing feature engineering with time-based variables (hour, day-of-week) and weather features to capture demand patterns. Achieved strong predictive performance with MAE of 1.02 kWh and WAPE of 8.5% delivering accurate short-term demand estimation applicable to operational planning and energy management decisions.
Fashion Image-Based Recommendation System
June 1, 2026 – Present
Designed and implemented an image-based fashion recommendation system using CNN (ResNet) in TensorFlow extracting visual feature embeddings from fashion product images for similarity-based retrieval. Integrated k-NN for similarity search and deployed the end-to-end system using Streamlit with a SQLite backend delivering an interactive, production-ready recommendation interface.
RAG-Based Medical Assistance Application
June 1, 2026 – Present
Developed a Retrieval-Augmented Generation (RAG) pipeline integrating FAISS vector search with Large Language Models (LLMs) for semantic search and context-aware medical response generation. Grounded model outputs using trusted medical sources (PubMed, WHO datasets) significantly reducing LLM hallucinations and improving response reliability and clinical accuracy for medical query resolution.
Bank Term Deposit Prediction Risk Classification
June 1, 2026 – Present
Built an end-to-end binary risk classification model on 41,000+ customer records to predict term deposit subscription likelihood achieving 90.5% accuracy using XGBoost with optimized feature selection. Identified key risk predictors (call duration, previous campaign outcomes, pdays) through statistical correlation analysis enabling targeted, data-driven customer risk scoring and campaign optimization.
Oracle Cloud Infrastructure 2025 Certified Data Science Professional
Oracle
June 1, 2026 – Present
Introduction to Large Language Models (LLMs)
IBM SkillsBuild
June 1, 2026 – Present
Statistics Certification
GyanyanAI
June 1, 2026 – Present
Data Science with Python
Teachnook
June 1, 2026 – Present
Cultural Fit Analysis
The candidate's academic projects cover diverse areas like electricity demand forecasting, fashion recommendations, medical assistance (RAG), and bank term deposit prediction. This breadth of application, combined with internships, indicates a versatile interest in applying ML across different domains. The target role of ML Engineer aligns well with the candidate's demonstrated technical skills and project focus. The certifications further show a commitment to continuous learning and skill development.
Soft Skills & Operational Fit
The candidate's project descriptions highlight problem-solving skills and an ability to deliver end-to-end solutions. The academic projects and internships suggest a proactive learning attitude and a focus on practical application of ML concepts. However, without direct interview data, assessing collaboration, stress handling, and work attitude remains speculative.