Senior Data Scientist
2019 - PRESENTAdobe- Developed AI-driven filters to help marketers to extend their audience using historical and real-time data of campaigns' success and failure. Results are a lift of up 25% on the audience and a boost of about 7% on the success rate.
- Led the development of a machine learning solution to optimize the right time to send marketing emails in order to increase the open rate. Current A/B testing results show a double open rate.
- Led AI projects for the conversation marketing platform. From text representation models to language models and natural language understanding, NLP, and computer vision.
Technologies: Adobe InDesign, New Relic, Apache Airflow, Google Cloud Platform (GCP), SQL, Python, Statistics, Deep Learning, Machine LearningData Scientist
2017 - 2019SAP Labs- Developed real-time monitoring of procurement expenses to propose materials for (re)negotiated contracts. Procurement strategic purchasers can be able to reduce the processing time from an average of two months to three days.
- Developed a machine learning model to assign a risk score to each purchase requisition in order to automatically approve it based on SAP WorkFlow data. Improved on data consistencey and reduced the approval time-interval to seconds.
- Developed a machine learning solution for invoice-to-account matching to reduce the processing time, improve the consistency and reduce related accounting errors/frauds.
- Led the development of a compliance tool. Gathered daily news about a given company, curate, and label each news article to the type of risk or opportunity with respect to compliance. Each company would be given a number of scores on a dashboard to inform the compliance specialists about what actions to make or advice to offer to the executives.
Technologies: TensorFlow, Adobe InDesign, Google Cloud Platform (GCP), JavaScript, SQL, Python, Statistics, Deep Learning, Machine LearningPhD - Research Assistant
2013 - 2017Brandeis University- Investigated synchronization in non-linear oscillators using the Belousov-Zhabontisky reaction as experimental medium. My work consisted of designing experiment, data collection, data analysis, and mathematical modeling.
- Built a computer vision and mechanical empowered robotic system that could autonomously control all of the experiments. Reactions were generated in droplets and deposited on microlithographic chips.
- Developed a programmable illumination microscope controller to excite or inhibit droplets using different light colors. This was achieved by using computer vision technology to track droplets and their status in real-time.
Technologies: Arduino, COMSOL, MATLAB, Python