Applied AI/ML practitioner and technical leader with experience building production real-time decision systems and conducting academic research in applied mathematics, scientific machine learning, and fluid dynamics. My industry work focuses on adaptive ML systems that make decisions under uncertainty, learn from experimental feedback, and connect model-driven policies to real-world outcomes.

Leadership

At The New York Times, I lead a team of ML scientists developing and deploying real-time ML models for subscription-related problems, such as serving a paywall at optimal moments or personalizing user-facing messages. Our production models serve millions of users and generate tens of millions of dollars in revenue, using causal ML, contextual bandits, personalization, and adaptive experimentation.

Applied AI/ML systems

As an IC and tech lead, I developed and deployed real-time causal ML models for multi-objective optimization of The Times paywall (see blog post). I also built large-scale production batch models that determined user-level access (see blog post, PyData talk, VentureBeat article). These systems were built in Python and Go for high-throughput inference on cloud-based containerized infrastructure. For representation learning, I have trained transformer encoder models using tokenized sequential user activity, generating embeddings for predictive tasks.

I am interested in causal inference and have used techniques like Meta-Learners and Sequential Trial Emulation, as well as designing RCTs.

Research

My Ph.D. thesis advised by Prof. Jörn Dunkel (Applied Mathematics), combined scientific ML, numerical computation, and fluid dynamics. I built a computational inference framework to learn PDEs from microscopic simulation and experimental data of active matter (see PNAS article) and contributed to early demonstrations of Neural Partial Differential Equations (see preprint). My research was partially supported by the Mathworks Engineering Fellowship.

I completed my Master’s at MIT on the fluid dynamics of internal waves and my B.Tech at IIT Madras in theoretical fluid dynamics. I also built an omni-directional robot for ABU Robocon (that’s me driving!).

Outside of work, I enjoy long-distance running in the summer and skiing in the winter.

See my CV for more details.

Skills

ML / AI

Representation Learning, Transformer encoder models, Scientific Machine Learning, Contextual bandits, Bayesian methods (Thompson Sampling, Bayesian Optimization), Causal Inference, Causal Machine Learning, Neural Differential Equations

Mathematical Modeling

Differential Equations, (Fluid) Dynamical Systems, Optimization, Linear Algebra, Numerical Methods for PDEs

Technologies

Programming

Machine Learning

ML Deployment