Sai Rakshith Potluri Email & Phone Number

Seattle, WA, US

Seattle, Washington, United States

Chicago, Illinois, United States

• Spearheaded the migration of the entire legacy database to Microsoft Azure Fabric Environment, leveraging SharePoint Lists for data integration. Developed a real-time client case management tool utilizing PowerBI.
• Engineered and implemented automated scripts for generating due diligence reports, and created a geospatial dashboard integrating ArcGIS with PowerBI. This innovation provided strategic insights into potential areas.
• Optimized SQL queries to significantly improve the efficiency of the client's data warehousing operations.

• Harnessed PyTorch, YOLOv7, and Image Augmentation to heighten wild capuchin identification accuracy from 85% to 92%.
• Implemented a real-time identification system in a wildlife sanctuary utilizing edge processing for efficient on-site analysis

Atlanta, Georgia, United States

• Crafted a streamlined Question Answering chatbot that blends Large Language Model capabilities with industry-specific knowledge to significantly elevate customer query resolution.
• Collaborated to enhance NCR's Knowledge Repository through Retrieval Augmented Generation using tools like Microsoft Azure, Databricks, Chat-GPT and LangChain, to optimize solution search beyond basic keyword matches.
• Integrated FAISS vector databases and utilized LLM embeddings for content extraction to ensure precise context retrieval.

Atlanta, Georgia, United States

• Engineered PySpark pipelines, unifying disjointed retail sales data to form a comprehensive promotional dataset.
• Employed Regression Analysis to discover and quantify 'pantry loading' behaviors in a vast segment of 202 product categories.
• Designed a predictive sales framework accounting for post-promotion sales dips, highlighting an opportunity to optimize supply chain practices and indicate potential annual savings of up to $485,000 for a flagship.

Project: AI Forest - Cognition in the wildBuilding custom computer vision pipelines to recognize and track capuchin monkeys of the same species in real-time.The project is a recipient of Georgia Tech and Emory University's prestigious AI.Humanity seed grant, supervised by Dr. Jacob Abernethy of the College of Computing at Georgia Tech and Dr. Marcela.

Atlanta, Georgia, United States

Research Assistant at Georgia Tech School of Public Policy.

• Implemented PySpark-based Extract Transform Load (ETL) pipelines, enhancing data computational efficiency by 41%, thereby streamlining downstream applications such as Customer Segmentation and Anomaly Detection..
• Developed a digital twin model using LightGBM and XGBoost to predict internet download speeds and perform root cause analysis. Through intricate feature extraction, data curation, and hyper-parameter tuning on.
• Engineered a SHAP-based explainability engine as part of a proactive and preventive intelligence strategy. This tool dynamically generates reason codes for sub-optimal 4G/5G download throughput, which has resulted in.
• Acted as a vital liaison between data engineers and business stakeholders, ensuring seamless communication and collaboration.

• Researched multiple behavioral models for autonomous navigation using Reinforcement (RL) and Imitation Learning (IL).
• Finalized the 'Learning by Cheating' method, implementing it through Tensorflow, OpenAI Gym, and CARLA.
• Devised a pipeline that leverages Mask-RCNN and IOU Tracking to seamlessly transform raw traffic camera feeds into distinct vehicle trajectories. With this strategy, we achieved a 100% surge in our trajectory dataset.

Bengaluru Area, India

• Developed and deployed a Java-based tool on in-house cloud instances that allows users to query past data from Apache Kafka logs. The tool significantly decreased the time taken (approximately 21%) to query gigabytes.
• Gained in-depth knowledge in developing horizontally scalable big data solutions in a Kafka ecosystem and full-stack development.

Hyderabad, Telangana, India

• Performed statistical analysis and data interpretation of game data to assist in skillset identification and personality analysis.
• Modelled a neural network to predict the psychological traits of an individual from their game data

• Designed and developed an android application which provides a common platform for patients, doctors andpharmacies.
• Used NoSQL Google Cloud FireStore for data storage.
• Conducted regular meetings with various stakeholders and developed the application accordingly, making it ready for deployment by the end of my tenure

Master Of Computational Data Analytics

Activities and Societies: Data Science @ GT

Master Of Technology, Computer Science, 3.66/ 4.00

Dean's Merit List