Shady Ali
Computer Science, University of Minnesota - Twin Cities (Graduation: May 2026)
Undergrad Researcher @Minnesota NLP
Currently doing undergraduate research on Test-Time and Inference Scaling, and Knowledge Discovery in Language Models at Minnesota NLP under the supervision of Professor Dongyeop Kang (DK).
Open for any work opportunities for Summer 2026 and beyond.
Research Interests (still refining them)
I have research and industry experience in Machine Learning and Data Science. And a strong foundation in Computer Science and Software Engineering principles and understand and practice software development life cycle and architectural design.
Recent Updates
Skills & Expertise
Languages
AI & Data Science
Developer Tools
Research & Publications
Engineering & Work Experience
Language Modeling from Scratch
Implemented Word2Vec (Skip-Gram, Negative Sampling), Neural Probabilistic Language Models, and N-Grams to build foundational language modeling concepts from the ground up.
View project →Agentic Marketing Campaign System
Developed an autonomous RAG-powered Agentic system that generates marketing campaign architectures by integrating past campaign data, client-specific market analysis, and research insights.
LLM-Powered Resume Extraction Pipeline
Built an LLM-powered resume extraction pipeline using a multi-threaded producer-consumer architecture for efficient processing, aggregating multi-source candidate data into Google Sheets with structured insights.
Customer Retention & Churn Prediction
Led a customer retention project, delivering a proof of concept with clustering (K-Means, GMMs) and churn prediction models (XGBoost, LSTMs) for customer segmentation and retention insights.
Explicit Content Detection App
Developed a PyTorch-based image classifier based on MobileNetV3 with 96% accuracy on 12,000 images and created an Android app for content blocking.
Text Sentiment Analysis Model
Trained an LSTM Network on 1 million texts from Twitter interactions and movie reviews with 87% accuracy, and deployed it as an API endpoint.
View project →Experience
- Working on Test-Time and Inference Scaling, and Knowledge Discovery in Language Models.
- Guiding visitors with AI/ML tasks, projects, and questions.
- Building Machine Learning systems for the space and UMN.
- Creating AI workshops and guides for students.
- Developed a data-oriented work scheduling and headcount report.
- Performed association analysis and clustering for a performance-scoring system to rank employees by hourly efficiency.
- Developed an autonomous RAG-powered Agentic system that generates marketing campaign architectures by integrating past campaign data, client-specific market analysis, and research insights.
- Built an LLM-powered resume extraction pipeline using a multi-threaded producer–consumer architecture for efficient processing, aggregating multi-source candidate data into Google Sheets with structured insights.
- Led a customer retention project, delivering a proof of concept with clustering (K-Means, GMMs) and churn prediction models (XGBoost, LSTMs) for customer segmentation and retention insights.
- Extracted, cleaned, and engineered features from millions of customer records to build robust datasets for model training and testing.