•Researched and implemented survival-based machine learning algorithms to predict cancer patterns using time-to-event techniques, showing vast improvements over traditional linear models•Conducted statistical analysis in R to determine significant cancer promoting genes, eg. performing multivariate regression, multiple hypothesis testing, and survival analysis•Extracted and aggregated large-scale tumor sequencing and patient EHR datasets to analyze genetic markers associated with cancer metastasis, leading to insights into 100+ new organ-specific genetic drivers•Managed and processed extensive datasets, ensuring data integrity, normalization, and standardization for effective machine learning training and validation•Leveraged visualization libraries to effectively present and communicate key insights

•Architected a large-scale, multilingual news aggregation system to provide clients with critical financial information across global markets•Boosted news language recognition capacity by 15x and expanded market coverage to 20 additional countries, integrating OpenAI models for language translation and text-summarization•Optimized news collection, cleaning, and database storage using AWS cloud computing, enhancing concurrent request capacity 30-fold and significantly reducing infrastructure cost•Integrated and maintained a PostgreSQL database, ensuring efficient and organized storage of millions of aggregated news articles for seamless retrieval and analysis