I am a Data Scientist and ML Engineer based in New York with over three years of professional experience, holding a Master of Science in Artificial Intelligence from SUNY Buffalo and a Bachelor of Technology in Electronics from India. My career began at IBM, where I spearheaded the development of a real-time recommendation engine using TensorFlow and Keras that significantly boosted user engagement within months of deployment. There, I optimized distributed training with Ray and Dask, automated ML pipelines using Kubeflow and MLflow, and deployed production-grade models on AWS SageMaker, Google Cloud AI, and Azure Machine Learning. I also integrated SHAP and LIME for model interpretability, built ETL pipelines with Apache Airflow, processed large-scale data using Apache Spark, and applied NLP techniques with spaCy and BERT for text classification and entity recognition. Currently, as a Research Fellow at NYU's Urban Systems Lab, I apply my machine learning expertise to climate resilience, developing predictive models for urban heat islands, flood vulnerability, and infrastructure stress using large-scale geospatial, satellite imagery, and census data. I employ ensemble methods like Random Forest and XGBoost, build reproducible experimentation workflows in Python, and create interactive dashboards with Plotly and Tableau to translate complex model outputs into actionable insights for urban planners and policymakers. Across both roles, I have honed a full-stack ML skillset—from data preprocessing, feature engineering, and hyperparameter tuning to cloud deployment, experiment tracking with Weights & Biases and TensorBoard, and version control using Git and DVC—while consistently collaborating with cross-functional teams to deliver scalable, business-impactful data solutions.