Data Science with less than a year in Deep Learning & NLP
AI is analyzing your overall score…
Identifying your key strengths…
Evaluating your skill match against the job requirements…
Assessing your cultural and operational fit
Research Intern at University of Galway and Data Science graduate student at AMU, specializing in deep learning, NLP, and GenAI systems from architecture to deployment. Projects span multimodal classification, agentic AI workflows, and biomedical ML consistently built and shipped as working products.
Aligarh Muslim University
Master of Science · Data Science
N/A – June 30, 2026
Insight Centre for Data Analytics, University of Galway, Ireland
Research Intern
June 1, 2026 – Present
Ireland
Multimodal Fake Review Detection System
January 1, 2026 – June 1, 2026
• Developed end-to-end multimodal deep learning system using BERT (text) + Vision Transformer (image) achieving 99.72% F1-score on 12,254 samples; implemented novel Cross-Modal Attention architecture for detecting text-image inconsistencies in fraudulent reviews. • Engineered feature extraction pipeline: 768-dim BERT embeddings + 768-dim ViT embeddings with attention-based fusion; conducted ablation study and SHAP explainability analysis revealing equal importance of text (48.7%) and image (51.3%) modalities. • Benchmarked 7 classification models (Logistic Regression, XGBoost, LightGBM, FFNN, CMA, GNN, Naive Bayes) using Tensorflow; implemented data preprocessing including mean imputation, KNN imputation, and stratified sampling. • Deployed as interactive web application on Hugging Face Spaces for real-time inference; users can upload review text and images to get authenticity predictions.
View ProjectConversational AI Lead Generation Agent | AutoStream
January 1, 2026 – June 1, 2026
• Engineered a LangGraph agentic workflow routing 3 intent types (greeting, inquiry, purchase) across multi-turn conversations automatically. • Engineered a FAISS-based RAG pipeline with Sentence Transformers to retrieve accurate answers from a curated knowledge base, eliminating hallucinations. • Implemented a conditional lead capture mechanism recording Name, Email, and Platform only after confirming buying intent, storing data in CSV. • Deployed Flask chat interface with voice responses; conversation state persists across 10+ dialogue turns via LangGraph state management.
View ProjectParkinson's Disease Detection | Multi-Model ML Pipeline
January 1, 2025 – December 31, 2025
• Benchmarked 7 classifiers - Logistic Regression, Naive Bayes, KNN, Random Forest, SVM, XGBoost, Custom ANN on 195 biomedical voice samples. • Applied SMOTE post-stratified split to resolve class imbalance (147 PD vs 48 healthy) without leaking synthetic samples into evaluation. • Custom ANN with L2 regularisation and early stopping achieved 97.44% accuracy, 100% precision, 96.55% recall, F1 0.98, ROC-AUC 0.99. • Reduced XGBoost overfitting via manual regularisation - max_depth, subsample, colsample_bytree, improving test accuracy to 87.18%.
View ProjectImpact of Social Media on Student Mental Health Statistical Study
January 1, 2024 – December 31, 2024
• Conducted a stratified random sampling survey of 200 students at Women's College AMU on social media and mental health. • Performed hypothesis testing in R; found 58.4% reported negative academic impact, 53.7% experienced loneliness, 56.7% had mood changes. • Validated effects on sleep quality and focus through chi-square and t-tests, producing a peer-reviewable statistical report.
IBM Data Analysis with Python
Cognitive Class (IBM)
June 1, 2026 – Present
IBM Machine Learning with Python
Cognitive Class (IBM)
June 1, 2026 – Present
Python for Machine Learning
Kaggle
June 1, 2026 – Present
Python Fundamentals Meets AI Workshop
Marine Technology Society, AMU
June 1, 2026 – Present
Deep Dive into AI Workshop
Marine Technology Society, AMU
June 1, 2026 – Present
Cultural Fit Analysis
The candidate's project portfolio shows a strong inclination towards innovative and impactful applications of data science, aligning well with a culture that values research, development, and practical deployment. The academic background and continuous learning through certifications suggest a growth mindset. The diversity of projects (healthcare, lead generation, fake review detection) indicates a broad interest and ability to adapt to different problem domains.
Soft Skills & Operational Fit
The candidate demonstrates strong problem-solving skills through complex project implementations. The ability to work on diverse projects, from statistical studies to advanced AI agents, suggests adaptability and a proactive learning attitude. The current research internship indicates a collaborative mindset and engagement with cutting-edge research.