Leading a distributed and cross functional team of product managers, scientists, and engineers developing Amazon’s Sponsored Products bidding systems, controls, and recommendations.

Leading applied science teams across the US and India working on computer vision, multimodal, and generative AI products within the Physical Stores Tech research org.

AML is a centralized function consisting of ~100 engineers, scientists, managers, senior managers, and product managers. The org contains product facing groups (working on problems like trust and safety, personalized recommendations, and dynamic pricing) as well as platform teams (working on self service and managed MLOps / data platforms while also providing high touch consulting services and embedded staffing). Developed the original vision for the team, advocated for its formation, and built the team up from inception.

The Revenue Optimization team works on business-facing data and ML problems such as lead prioritization to maximize sales productivity, inventory forecasting, and customer LTV modeling.

Tech lead for the ads targeting team, working with large datasets for analysis and machine learning tasks, mentoring other engineers on the team, and guiding overall system design. Involved in projects such as CTR and conversion prediction, relevance targeting and auction pricing, and revenue forecasting.

Developed high frequency trading signals and systems across various asset classes and exchanges.

Researched, backtested, and developed systematic and stat-arb trading systems and strategies for the quantitative credit and energy trading teams.

Instructed students through lab projects to acquire GPS satellite signals via an open-source receiver board, decode the signals through DSP filtering, and compute positional estimates for the GPS boards.

Analyzed ionospheric imaging data using various signal processing techniques to extract information and statistical classification/machine learning methods to detect anomalies.