Detail-oriented, fast-paced, and analytical problem solver dedicated to achieving demanding development objectives while producing impeccable code.
Overview
5
5
years of professional experience
1
1
Certification
Work History
Software Engineer
Plaid
03.2022 - Current
Developed secure, high-performance API solutions for financial data integration, supporting thousands of financial institutions and enhancing the user experience for millions of customers
Instrumental in the architectural redesign for improved transaction processing, achieving a 10% increase in throughput and a 15% decrease in latency, directly impacting customer satisfaction
Led the implementation of machine learning algorithms for real-time fraud detection, preventing millions in potential fraud and establishing Plaid as a leader in secure fintech solutions
Initiated a company-wide quality improvement program, integrating best practices in code review, automated testing, and CI/CD, improving code deployment efficiency and quality
Software Engineer
Bank Of America
05.2019 - 03.2022
Developed and implemented a machine learning-based fraud detection system by leveraging Python and TensorFlow. This system utilized advanced algorithms (such as Random Forest and Neural Networks) to analyze transaction patterns, achieving a significant reduction in fraudulent transactions
Integrated real-time analytics into the bank's transaction processing system using Apache Kafka for data streaming and Elasticsearch for real-time search and analytics, enhancing the detection of suspicious activities through improved data visibility and processing speed
Engineered RESTful API using Node.js and Express to facilitate secure, real-time data exchanges between the bank's fraud detection platform and third-party data sources, enriching the fraud detection capabilities and increasing overall detection rates by 15%
Led the adoption of AI-driven predictive analysis tools, utilizing PySpark for distributed data processing and machine learning to refine fraud detection models. This effort significantly reduced false positives by applying Gradient Boosting and SVM algorithms for more accurate predictions
Implemented end-to-end data encryption and security protocols within the fraud detection pipeline, using AES for data at rest and TLS for data in transit, ensuring compliance with GDPR and PCI DSS standards while safeguarding customer data integrity