About
Data Science and AI professional with hands-on experience in LLM evaluation, machine learning, model validation, data validation, statistical analysis, anomaly detection, and predictive modeling. Experienced in evaluating AI/ML model outputs, identifying performance inconsistencies and limitations, validating datasets and predictive models, and translating analytical findings into structured documentation and actionable observations.
Experience3
Graduate Engineer Trainee
Jul 2026 — PresentBaxy Limited
Perform data validation and diagnostic analysis to identify inconsistencies, anomalies, abnormal patterns, and data-quality issues. Analyze technical and engineering information to identify trends and support data-driven operational decisions. Translate analytical findings into structured reports, documentation, and actionable observations for engineering stakeholders. Develop and maintain Standard Operating Procedures (SOPs) to improve consistency and standardize technical workflows.
AI Research Associate Intern
Sep 2025 — Oct 2025Overload Ware Labs AI · Internship
Evaluated LLM outputs across quality, reliability, consistency, scalability, and business applicability for AI/ML use cases. Conducted comparative analysis of AI model responses to identify performance patterns, inconsistencies, limitations, and potential failure modes. Analyzed model behavior across different prompts and use cases to assess output reliability and response consistency.
Data Science Intern
Jan 2025 — Jun 2025Intellipaat Software Solutions Pvt. Ltd. · Internship
Processed and validated large datasets using Python to improve data quality and analytical reliability. Performed EDA, anomaly detection, trend analysis, and pattern identification to identify data issues and actionable insights. Engineered features and applied statistical techniques to prepare datasets for predictive modeling. Developed and validated ANN and RNN models for predictive analytics and forecasting.
Projects2
GenAI Model Risk Assessment & LLM Evaluation Framework
Designed a structured evaluation framework to assess LLM systems across accuracy, consistency, robustness, bias, explainability, hallucination, and misuse risks. Developed test cases and prompt variations to evaluate model behavior, prompt sensitivity, output consistency, and failure modes. Performed comparative analysis of LLM responses and documented identified risks, limitations, and performance observations. Conducted a control and gap assessment covering model documentation, monitoring, human oversight, testing, and responsible AI controls. Prepared structured validation documentation containing test methodology, evidence, observations, identified risks, and recommended controls.
- Python
- LLMs
- Model Validation
- AI Risk
- Responsible AI
Customer Churn Prediction & Model Validation
Built and evaluated Logistic Regression, Decision Tree, Random Forest, and Neural Network models for customer churn prediction. Performed feature engineering and Recursive Feature Elimination (RFE) to identify predictive drivers from 20+ attributes. Applied stratified train/test validation and confusion matrix analysis to evaluate model performance. Compared model results to assess predictive performance and select an appropriate modeling approach. Achieved approximately 79% accuracy with an interpretable Logistic Regression model.
- Python
- Scikit-learn
- Machine Learning
- Neural Networks
Education3
Master of Science (M.S.) in Data Science & Artificial Intelligence- Top Up
2026European Global
Advanced Certification in Data Science and AI
2024 — 2025I-Hub Divya Sampark – IIT Roorkee & Intellipaat
Bachelor of Engineering (B.E.) in Electronics and Electrical Engineering
2020 — 2024MBM Engineering University
Certifications2
Advanced Certification in Data Science and AI
2025I-Hub Divya Sampark – IIT Roorkee & Intellipaat
Yuva AI for ALL
2026FutureSkills Prime