Applied Machine Learning Scientist

Develop production machine learning pipelines for personalized product ranking, recommendation, and customer decisioning across multiple lines of business. Design customer-level ranking strategies for more than 60 campaigns and products using model propensity, eligibility, campaign context, historical performance, and expected business value.

Build scalable feature engineering, target generation, scoring, ranking, calibration, and evaluation pipelines using Python, SQL, PySpark, and Azure Databricks. Evaluate predictions against historical outcomes, monitor model behavior, report actionable findings to leadership, and partner with engineering, validation, privacy, compliance, and business teams.

Designed and ran computational experiments using statistical and causal methods, including Double Machine Learning and uplift modeling, to evaluate approaches for complex financial problems.

Conducted research on fairness and bias mitigation in financial machine learning. Documented and presented technical findings to interdisciplinary collaborators, including work presented at the ICLR 2025 Advances in Financial AI Workshop.

Applied machine learning and computational modeling to interdisciplinary scientific research, including quantum machine learning for protein design.

Designed computational investigations, analyzed results, and documented findings for peer-reviewed research publications and technical presentations.

Applied computational methods and quantitative analysis to interdisciplinary research problems.

Supervised and mentored more than 10 graduate and undergraduate students in C++ programming and computational methods.

PhD in Computational Physics.

Master of Science in Physics.

Bachelor of Science in Physics.