Sashank Kuraganti

- Developed physics-informed deep learning models using TensorFlow for AIx™ platform, processing 5,000+ real-time sensor streams via PySpark and Kafka, improving process window stability by 60% in GAA and HBM fabrication. - Built and deployed computer vision pipelines using OpenCV, CLIP, and custom CNNs on AWS SageMaker and Kubernetes, enabling automated defect classification in eBeam review tools and reducing manual review time by 45%. - Designed RAG-enhanced LLM system (LlamaIndex + LangChain + private fab data in Pinecone/FAISS) for rapid materials knowledge retrieval, cutting new recipe development cycle from 6 weeks to 4 days (approximately). - Led MLOps implementation using MLflow, Kubeflow, and Airflow on Databricks Lakehouse, achieving 99.9% model deployment success rate and full traceability for ISO-compliant AI tools in production fabs. - Engineered XGBoost combined with Spark MLlib predictive maintenance models on over 3 years of chamber telemetry stored in Snowflake and Redshift, reducing unplanned downtime by 32% across 200+ etch/deposition systems. - Implemented Explainable AI (SHAP/LIME) dashboards in Tableau and Jupyter for model decisions in patterning and metrology, ensuring regulatory approval for AI-driven process control in customer fabs. - Fine-tuned multimodal models combining sensor time-series and SEM images, deployed via Ray Serve and FastAPI, boosting overlay accuracy in hybrid bonding by 28%.

- Developed NLP chatbots and recommendation prototypes for the 2022 Code to Give Hackathon using Python, Hugging Face Transformers, spaCy, and FAISS vector search. - Built and productionized client-segmentation and behavior-prediction models (Scikit-learn, XGBoost) on Databricks/Spark to improve wealth management reporting accuracy by 28% and advisor productivity by 35%. - Designed end-to-end data pipelines with PySpark, Airflow, and Snowflake to automate daily/weekly analytics feeds for risk and portfolio teams, reducing report generation time from 6 hours to under 15 minutes. - Created interactive Tableau and Power BI dashboards consumed by thousands of internal users and external clients, replacing manual Excel reports and cutting average dashboard build time by 60%. - Performed A/B tests and statistical analysis on new digital features for E*TRADE/Morgan Stanley client platforms, directly influencing product decisions that drove 18% higher user engagement in rolled-out features. - Collaborated with full-stack and infrastructure engineers in Alpharetta to containerize models (Docker) and deploy via internal CI/CD, ensuring reliable daily scoring for 2.5 million+ client accounts with 99.9% uptime.

- Built and optimized ETL pipelines using Python, SQL, and AWS Glue to process millions of daily pharmacy claims, reducing data latency from hours to minutes for real-time member eligibility checks. - Led data migration efforts from legacy databases to Amazon Redshift, standardizing formats for Aetna-CVS integrations and enabling seamless reporting across business units. - Designed automated workflows with Apache Airflow to handle batch and streaming data from various sources, supporting AI automation for prescription intake and benefits verification. - Collaborated with cross-functional teams to create secure data pipelines on AWS, incorporating quality checks that improved accuracy in HealthHUB virtual care assessments. - Developed simple dashboards in Tableau to visualize pipeline performance and data flows, helping stakeholders monitor cloud migration progress and troubleshoot issues quickly.

- Used Python (Pandas) and SQL to clean, merge, and prepare sensor and project data that supported daily construction and engineering reports. - Assisted in moving legacy project datasets from on-prem systems to Azure Data Lake, making data easier to access for remote teams during COVID. - Developed simple Python and Shell scripts to automate daily data updates for supply-chain and project-tracking teams, reducing repetitive manual work. - Performed data quality checks and created basic Power BI dashboards to show project timelines, delays, and risk indicators for major infrastructure projects. - Helped the team configure Kafka to bring streaming updates into early digital-twin prototypes built at the Powai R&D center. - Supported renewable-energy analytics by organizing structured datasets and loading them into Azure SQL / Synapse for reporting and grid-integration studies.