• Developed the Azure OpenAI Batch Accelerator. The accelerator is a reference implementation for leveraging the Azure OpenAI Batch API to process large sets of files in Azure Data Lake Storage. It provides a flexible configuration, including support for continuous or one-time processing of batch files. The project is designed for extension and testing, rather than production use, and facilitates the automated processing and cleanup of files, metadata generation, and error handling. The tool is ideal for those looking to integrate Azure OpenAI capabilities into batch processing workflows• Led the design and development of a prototype for the automated extraction, categorization, and analysis of medical literature for automated comprehensive literature review. The prototype developed is configurable and uses GPT-4o along with the Azure Document Intelligence service to segment, analyze, and extract data from PDFs, presenting the results to the user in an aggregated structured output. Early estimates project a significant reduction in workload for end-users along with 100s of thousands in terms of cost savings. • Led the design, prototype development, and provided production development guidance of a cloud-native platform for the identification and explanation of transactional anomalies in complex financial data, using machine learning, for a major pharmaceutical company. The project uses gradient-boosted decision trees to automatically identify anomalies and then, along with specific context information, uses GPT-4o to explain those anomalies.• Led the prototype development of a machine learning-based recommendation system for fine-grained sales data. The prototype model demonstrated a deal classification accuracy of over 92% and the project is currently being further developed internally by the customer.

• Led the design and prototype development of an Azure-based smart analytics platform for the aggregation and analysis of large amounts of medical device data using big data processing technologies (e.g., Spark). Our platform was capable of cost-effectively analyzing over 400 million rows of data in minutes to generate insights, find emergent patterns, and identify at risk patients using a combination of machine learning as well as statistical analysis techniques.• Led the design, prototype development and guided production development of a smart supply chain project for one of the largest global pharmaceutical & consumer goods manufacturers. The project involved analyzing and transforming large amounts of supply chain data using Spark, Azure Data Factory, and Azure Data Lake Storage (Gen2). The project is generating over $200K/month in revenue and led to a cost reduction of 10s of millions for the customer.• Part of the prototype development team for the next-gen Data-as-a-Service platform for one of the largest global pharmaceutical & consumer goods manufacturers. Responsible for using Spark streaming to ingest and transform 24K events/sec in under 5 minutes/micro-batch on top of 1200 tables with 30 billion entries as part of a competitive assessment. Our solution was the only technically viable solution with an end-to-end processing time of ~2 minutes/micro-batch and is in the final stages of procurement with an estimated worth of $15 million.• Led the design and prototype development of Phase 1 and Phase 2 of a COVID-19 tracking application which had an extremely aggressive 2 week go live date due to the pandemic. The application uses Azure Functions, Azure Data Factory, and Azure Synapse to ingest and process patient COVID-19 data. The project is currently live, and the team is evaluating the Phase 2 design.

• Part of leadership team leading development and analytics effort resulting in $2.5 million in pre-series A funding.• Designed and lead development of a Java-based, REST-driven parallelized version of log analysis using RabbitMQ leading to a significant boost in overall performance. • Designed and lead development of a Java-based REST-driven parallel storage module using RabbitMQ leading to significantly higher data ingestion throughput to Apache Cassandra/Amazon S3.• Frequently worked with customers to create, update, and install (using Ansible) various light-weight python data collection daemons.• Responsible for working with the sales team to give technical sales pitches as needed. Responsible for the start of several prototypes as well as the acquisition of several SaaS customers. • Worked with customers to apply InsightFinder’s Java-based unsupervised, stream-based machine learning technology to complex infrastructures to improve system availability.

• Designed and lead development of a Java-based REST-driven big data encryption and storage platform capable of authentication, key generation, encryption, metadata creation, and storage of large (1GB+) files.• Designed and lead development of a Java-based REST-driven key management service capable of generating encryption keys, assigning role-based access controls, and encrypting data. • Collaborated with IBM-China to develop a tool for the automatic mapping of ambiguous medical schemas (e.g., HL7) to known data schemas using machine learning techniques. • Part of a secure Spark-as-a-Service development group responsible for executing critical PoCs with large health care companies. • Worked with various sales teams as technical sales engineer both internationally and domestically.

Responsible for conducting systems research related to performance anomaly prediction and diagnosis in virtualized cloud environments. Responsible for the design, implementation, and testing of the various tools developed. Responsible for helping to advise junior students on the progress of their graduate research.

Software developer for a small software group affiliated with MUSC. Responsible for all design,development, and testing. Worked primarily on database driven projects using PHP, Java, Javascript, AJAX, and SQL.