I lead machine learning and NLP efforts at Statt - working extensively with a large dataset of millions of public policy-related documents. Details include: - Built/trained model to classify documents as relevant to public policy - goal was to weed out bad documents from our data collection. - Built/trained model to classify documents with respect to type (white paper, commentary, press release, etc) - which greatly expanded search capabilities of the product.- Employed over a dozen topic classification models to classify documents as discussing various public policy-related topics such as economics, housing, and transportation.- Developed data collection and labeling strategies for these models for model training from our existing corpus of documents (which number in the millions).- Developed and deployed state-of-the-art entity linking solution in PyTorch which greatly expanded the data collected from each of our documents.- Developed text summarization service built on existing model that was fine tuned with relevant training data. These summaries appear in the application to provide users with a brief synopsis of each article.

Machine Learning Engineer working on entity extraction, tagging, and other NLP-based applications to process news, financial filings, and the like.

Building the newest platform for geopolitical and financial analysis

Using Python and the bank's Quartz framework, I built the Bookmap application backend and UI using REST-ful web services and an MQ-based solution for middleware.This involved working with massive data sets of trading books and user information.

Built intelligent bot framework in Python to unify all the different components of the Axon Vibe platformDesigned and built platform to intelligently match Swiss train schedules from data points provided by user mobile devices – used both Google and the Swiss Rail’s own API to match schedule information with this data (both geographic coordinates and mode of transportation)Built platform using TensorFlow to learn a user’s mode of transportation from data from a mobile device

Part of the Stress Framework and Country Risk team for Gauss - Gauss is a full revaluation, Monte Carlo simulation engine and it computes the credit exposure if the counterparty defaults. Gauss uses the latest cutting-edge technology such as Python, high performance grid computing and performs over 3 trillion MTM calculations in its daily calculation run.

Development of the Quartz Platform - primary trading and risk platform for Bank of America. Specifically worked with the Prime Brokerage and Margin Risk team in building new products and refactoring existing code to make it more efficient.Managed extremely large data sets and built systems to apply various calculations across millions of positions and trades.Development of complex applications to manage Bank’s risk and margin business.Usage of Numpy, Scipy, Pandas, and Bank’s proprietary data management libraries.

As Pre-Sales Engineer, I am responsible for understanding and managing the technical aspects of the client's business. I also run the technical components of the sales team locally in New York, providing everything from product demonstrations to proof-of-concept projects that align with client needs. Additionally, I am tasked with providing a deep understanding of the underlying trading marketplace.From a development perspective, I have worked on projects building custom engines for our clients in Java and Python, including a bespoke OMS and aggregator of FX liquidity.About smartTrade Technologies:Founded in 1999, smartTrade provides sophisticated liquidity management systems, enabling banks to develop multi-asset dealing platforms that aggregate liquidity from dozens of sources to create a single order book, distribute customized pricing to clients, receive and manage client order flow, internalize liquidity and/or route it to external venues while managing state throughout the order lifecycle, implement smart order routing and a proprietary algorithms, and connect electronically to any number of venues regardless of messaging protocols. The system handles multiple asset classes and is in production globally supporting foreign exchange, fixed income, equities, rates, and many other instrument types.

Technical Account Manager specializing in consulting and management of large projects designed to mitigate operational and trading risks for financial services firms, including exchanges, sell-side banks, and hedge funds.ITRS Group leads the way in a new discipline that extends real-time monitoring into a comprehensive operational and service management solution. Providing innovative businesses with the visibility necessary to identify, analyze and mitigate risk, ITRS Group has been recognized through industry awards for our innovation and customer support. Our products are specifically designed to reduce service disruption, improve IT efficiency, and ensure that critical operational processes are executed as planned, protecting against both business reputation and trading risk. Established in 1997, ITRS has offices in London, New York and Hong Kong supporting clients worldwide including data vendors, brokers, exchanges, hedge funds and banks. ITRS has over 600 Geneos installations, implemented in 60 leading financial institutions, including eight of the top ten global investment banks.

Project Management - web and product development

Built and developed several social-media web applications in the Ruby on Rails framework - messaging applications, blogging platform, notifications system, user/session management, and bulletin board software.

Development associate working on low income and market-rate housing projects.

Completed a masters program in Development/Real Estate Finance at the University of Pennsylvania -worked on various projects dealing with valuation and revenue forecasts.

Led several Ruby on Rails projects from design to deployment, using TDD (Test Driven Development) as a guiding methodologyDeveloped Rails applications that also conformed to Web 2.0 standards, involving significant user interaction, Ajax, and dynamic user interface design.Extensive work with Rails e-commerce applications, shopping carts, and credit card processingExamples include: www.labwellness.com (beta), www.cbciweb.com/clients/

Developed several auction sites using PHP and the Google Maps API for companies to lease their land holdings. The application featured a complete content management system on the backend, mapping and GIS data on the front end, auctions and bidding, a complex email notification system, and dynamic PDF creation for licensing purposes.Developed a complex time tracking tool using ASP.NET 2.0 and SQL Server 2005. This application featured a multi-tier design that allowed the user to dynamically add projects and record time for each project added.Managed several sites simultaneously during development. Troubleshot site problems and bugs, worked with customers to find solutions to known issues.Designed a complete content-management system for Orbis’s main site, based off Joomla, Wordpress, and other similar open source applications. The system heavily utilized Ajax and Web 2.0 technologies, improving the user interface and user experience and lessening the load on the server.