Aastha Khatgarh

E

Data Analytics & Machine Learning Fellow Trainee

ElevateMe Bootcamp,

Jun 2025 - Current (1 year 5 months)

• Engaging in 150+ hours of hands-on learning and project work, including active participation in a live project and two optional capstone projects. • Apply data analytics and machine learning techniques to address real-world problems. • Utilize advanced tools such as Python, Jupyter Notebooks, Pandas, Numpy, Matplotlib, Seaborn, and Scikit-learn to build and evaluate machine learning models. • Deploy machine learning models on Microsoft Azure, integrating Azure ML with Azure SQL databases to enable real-time analytics and predictions. • Perform data preprocessing, feature engineering, and model selection, and evaluate regression, classification, and clustering algorithms to optimize performance. • Collaborate in a professional team e

AI Researcher

Northwestern University

Jan 2025 - Current (1 year 10 months)

• Developed a PPO-based reinforcement learning framework to unlearn restricted content from LLMs while preserving fluency and coherence. • Engineered a hybrid reward system to suppress specific tokens without causing catastrophic forgetting. • Initiated a project on automated LLM-based grading using rubrics, prior grading patterns, and course material. • Utilised PyTorch, Hugging Face Transformers, prompt engineering, PEFT, LoRA, and Reinforcement Learning while documenting experiments for collaborative research.

Data Science Intern

Allegion

Sep 2024 - Dec 2024 (4 months)

• Collaborated with cross-functional teams to analyze warranty claims using PySpark workflows and LLM-based extraction techniques. • Delivered insights across geography, product category, and time using OpenAI embeddings, clustering methods, and exploratory data analysis. • Proposed mitigation strategies that led to over 80% reduction in recurring claims by automating root cause analysis and categorization. • Worked with Python, NumPy, Pandas, Jupyter Notebooks, Power BI, and OpenAI API for data processing, visualization, and modeling.

AI Research Intern

Northwestern University

Apr 2024 - Sep 2024 (6 months)

• Designed and deployed a dual-mode LLM pipeline (live and batch processing) to automate key data extraction from global poverty research PDFs, reducing manual effort by over 60% . • Built and containerized front-end and back-end services using Docker, with model integration (Llama 3. 1 via AWS Bedrock and GPT-4) for answer extraction based on user-selected accuracy levels. • Engineered scalable AWS-based infrastructure using Lambda, S3, MongoDB, and CI/CD pipelines with GitHub Actions and CodeDeploy for real-time deployment and document processing.

About

Detail

Timeline

Résumé

Aastha Khatgarh

About

Detail

Behavioral traits