Data Science with less than a year in Machine Learning & Deep Learning
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 Scientist (Early Career) with hands-on experience in machine learning, deep learning, imbalanced classification, and end-to-end model deployment. Skilled in building scalable ML pipelines, handling imbalanced datasets, and deploying models using Flask and cloud platforms. Strong foundation in data analysis, model evaluation, and MLOps practices.
Fakir Mohan University
Master of Computer Applications
August 1, 2023 – June 30, 2025
GIET University
Bachelor of Technology · Chemical Engineering
August 1, 2017 – June 30, 2021
AI Emotion-Based Music Recommendation System
June 16, 2026 – Present
• Developed a real-time emotion detection system using CNN and transfer learning models (MobileNetV2, EfficientNetV2). • Trained models on FER-2013 and RAF-DB datasets, improving generalization across real-world scenarios. • Achieved approximately 75% accuracy through hyperparameter tuning, regularization, and data augmentation. • Built and deployed a full-stack application using Flask (backend) and React (frontend). • Integrated REST APIs and YouTube API to deliver dynamic, emotion-based music recommendations. • Optimized application performance for low-memory cloud environments (Render, Hugging Face).
Odia Text Recognition System
June 16, 2026 – Present
• Built an end-to-end OCR system for Odia script using CNN + BiLSTM architecture. • Implemented CTC loss to enable sequence prediction without character-level alignment. • Developed preprocessing, encoding, and decoding pipelines for text recognition. • Improved sequence prediction accuracy using deep learning-based feature extraction.
Deployment with Docker and Azure
June 16, 2026 – Present
• Developed a Flask-based web application for image upload and management. • Containerized the application using Docker for consistent and reproducible deployment. • Deployed the containerized app on Azure App Service and Container Instances with environment-based configuration. • Integrated Azure Blob Storage for storing images and PostgreSQL for managing image metadata. • Designed REST APIs to handle image upload, retrieval, and storage workflows.
Credit Card Fraud Detection System
June 16, 2026 – Present
• Built a fraud detection model on an imbalanced dataset using SMOTE and ML pipelines. • Trained and evaluated multiple models including Logistic Regression, Random Forest, and XGBoost. • Selected XGBoost based on precision, recall, F1-score, and ROC-AUC metrics. • Implemented experiment tracking using MLflow and automated workflows using GitHub Actions.
2nd Place, Inter-College Coding Competition
Unknown
June 1, 2026 – Present
Big Data Computing
NPTEL
June 1, 2026 – Present
Cultural Fit Analysis
The candidate's projects demonstrate a strong interest in diverse areas within Data Science, including computer vision, NLP (OCR), and traditional ML (fraud detection). The use of various tools and platforms (TensorFlow, Scikit-learn, Flask, React, Docker, Azure) indicates adaptability and a willingness to explore different technologies. The academic background (MCA in progress, B.Tech in Chemical Engineering) shows a transition into the target role, which can be a positive indicator of motivation and learning agility. However, the lack of professional experience means cultural fit cannot be fully assessed based on team collaboration or corporate environment exposure.
Soft Skills & Operational Fit
The candidate's project descriptions indicate a proactive approach to learning and applying new technologies. The focus on end-to-end solutions, from model development to deployment, suggests good problem-solving and operational awareness. However, without direct work experience, it's difficult to assess collaboration, stress handling, or communication in a team setting.