Experience

QuantumBlack, AI by McKinsey | September 2025 – Present

Conducting research and development of data science assets aimed at accelerating clinical trial optimization, enabling AI-driven trial identification, and building digital twin models for virtual patient simulation.

ZS Associates | June 2025 – September 2025

Worked on a GAN-based framework for Patient Digital Twins to simulate synthetic patient journeys aimed at clinical trial monitoring and risk prediction.
Utilizing Generative Adversarial Networks (GANs) and deep learning (PyTorch) to analyze multivariate, temporal health data and predict patient retention or dropout.
Enhancing early risk detection in clinical trials by creating high-fidelity synthetic patient data for simulation and intervention planning.
Built a Burden of Illness simulation tool by defining patient-level burden metrics using real-world data and delivering an interactive dashboard to simulate burden indices and identify key drivers (procedures, lab tests, visits).
Leading end-to-end analytics engagements to solve complex healthcare business problems using machine learning and statistical modeling.
Designing and operationalizing predictive models to drive strategic decisions.
Mentoring junior team members and guiding technical delivery.
Contributing to proposals and capability development by translating advanced data science techniques into scalable, client-ready solutions.

ZS Associates | July 2023 – June 2025

Created a risk stratification model using Cox Proportional Hazards regression to forecast adverse outcomes (ICU admission, IMV usage, readmission, mortality) in a COVID-19 patient cohort.
Emphasized feature selection, addressing class imbalance, and deriving clinically significant insights to inform early intervention strategies.
Findings currently under review for publication in partnership with clinicians and a scientific review board.
Developed a pipeline to identify fabrications and anomalies in clinical trials, assisting internal audit teams in detecting risk signals and enhancing confidence in submitted trial data.
Created an LLM-powered SQL translation framework to automate query adaptation across heterogeneous healthcare datasets without reliance on standardized data models.
Implemented adaptive context-reduction techniques to enhance query determinism and minimize LLM hallucinations by dynamically filtering schema-relevant metadata.

ZS Associates | February 2023 – June 2023

Developed a solution using hierarchical density-based clustering and BERT embeddings to extract key attributes from consumer reviews across multiple brands.
Implemented sentiment-based scoring metrics to identify popular brands based on review data.
Analyzed claims data to generate metrics for identifying healthcare providers and organizations for targeted digital therapy strategies.
Built a data quality framework on EMR data using business rules and anomaly detection across univariate, multivariate, and temporal spaces.

ZS Associates | November 2020 – January 2023

Worked on a proof of concept for a prospective support arm using real-world EMR data to generate synthetic comparator cohorts for prospective patient monitoring.
Conducted analysis of disease prevalence, comorbidities, treatment landscapes, and physician specialties using claims data.
Developed disambiguation methodologies using fuzzy matching, NER tagging, and business rules to identify key opinion leaders.

Accenture | June 2019 – August 2020

Developed tools for large-scale data migration to SAP systems using LSMW and LTMC.
Implemented ABAP report programs for analyzing work breakdown structures.
Built reporting utilities to identify and debug errors during mass data transfers.