AI Engineer with less than a year in ML pipelines, classification, and anomaly detection.
AI is analyzing your overall score…
Identifying your key strengths…
Evaluating your skill match against the job requirements…
Assessing your cultural and operational fit
B.E. student specializing in Artificial Intelligence & Data Science with hands-on experience building end-to-end ML pipelines for classification, anomaly detection, and predictive modeling. Proficient in Python, Scikit-learn, SQL, and data preprocessing workflows. Exposure to cloud foundations (AWS, Oracle Cloud) and Git-based version control.
Ajeenkya DY Patil School of Engineering
B.E. · Artificial Intelligence & Data Science
August 1, 2023 – July 31, 2027
Blend Vidya EdTech
Python Development Intern
November 1, 2025 – March 1, 2026
India
Return Risk Prediction System for E-Commerce
June 1, 2026 – Present
Developed an end-to-end ML pipeline for product return risk classification by combining structured customer behavior data with NLP-based sentiment analysis on product reviews. Executed feature engineering steps including text vectorization, encoding, and outlier treatment, then trained a Gradient Boosting classifier achieving strong precision and recall on an imbalanced dataset. Applied SHAP (SHapley Additive Explanations) to interpret model predictions and surface key drivers of return behavior, aligning output with responsible AI interpretability practices.
Anomaly Detection in Network Traffic
June 1, 2026 – Present
Built an unsupervised anomaly detection system to identify irregular patterns in network traffic logs using Isolation Forest and Local Outlier Factor algorithms. Performed comprehensive preprocessing — normalization, missing value imputation, and feature selection on unstructured network packet data to improve detection quality. Visualized flagged anomaly clusters and temporal behavior patterns to support root-cause analysis of abnormal system events.
Inventory Waste Prediction System
June 1, 2026 – Present
Engineered a classification model to predict high-risk inventory items prone to waste by analyzing demand patterns, product shelf life, and historical sales features. Conducted exploratory data analysis and feature engineering to extract signals from structured tabular data; tuned model hyperparameters to optimize precision for operational decision support. Generated actionable insights on over-stock risk to support supply chain planning, demonstrating practical ML application to a business problem.
AWS Cloud Foundations
Amazon Web Services
June 1, 2026 – Present
Oracle Cloud AI Foundation
Oracle
June 1, 2026 – Present
Google Machine Learning Crash Course
June 1, 2026 – Present
Python for Data Science
Udemy
June 1, 2026 – Present
Cultural Fit Analysis
The candidate's academic projects show a focus on practical applications of AI/ML in diverse domains like e-commerce, network security, and supply chain. Their internship experience in an EdTech company and participation in IoT and full-stack development competitions indicate a broad interest in technology and a willingness to learn and apply skills across different areas. This suggests a good fit for a dynamic, learning-oriented environment. However, the candidate is still an undergraduate with limited professional experience, which might impact their immediate cultural integration into a senior role.
Soft Skills & Operational Fit
The candidate demonstrates an ability to work on structured projects, manage code versioning, and document work, as seen in their internship. Their project descriptions indicate a problem-solving approach and an understanding of applying ML to business problems. However, there is insufficient data to assess stress handling, advanced team collaboration, or leadership potential.