Probability theory
Stochastic analysis
Anticipating stochastic calculus
Differential equations
Large deviation principles
Infinite-dimensional analysis
Statistics
Machine learning
Mathematical modelling
Mathematical finance
I am currently working on large language models (LLMs) as a Lead AI/ML Engineer at Optum.
📍 remote, US
📆 2024-10-28 onwards
Post PhD, I worked for over 2 years at Amazon as an Applied Scientist in the Reliability and Maintenance Engineering division.
Responsibilities
Worked on various constrained optimization problems, such as maximum flow optimization and optimal load-balanced job scheduling.
Text classification: Deployed a text classifier in SageMaker with data-derived heuristics for inventory change requisitions, enabling automatic processing of requests, subsequently used to design a time-saving UI.
Text summarization: Used LLMs in Bedrock to summarize and tag safety incident reports.
Worked on anomaly detection, clustering, and survival modelling for various projects.
Details
🏢 Amazon.com, Reliability & Maintenance Engineering
📍 Bellevue, WA, US
📆 2022-07-18 to 2024-10-18
During the final year of my PhD, I worked as a Data Scientist Intern at Amazon in the Reliability and Maintenance Engineering division.
Responsibilities
Anomaly detection: Developed an ensemble model (based on drift detection, Pareto principle, and Benford’s law) to detect anomalies in warehouse equipment effectiveness data, used to flag anomalous process paths.
Developed a text summarizer for machine-generated error logs from anomalous equipment.
Details
🏢 Amazon.com, Reliability & Maintenance Engineering
📍 Seattle, WA, US
📆 2021-05-17 to 2021-08-20
I worked at Mu Sigma, a business analytics company, as a researcher in the field of big data. My primary job as a data scientist was to develop and code parallelized algorithms such that they may be run on a distributed architecture using the MapReduce framework.
Implementing the following machine learning algorithms for big data using R on Hadoop
generalized linear model
exploratory data analysis
k-means clustering
Training
Supported clients (Fortune 500) with their big data project.
Was an organizational trainer for R, Hadoop, and related technologies.
Was promoted to Senior Business Analyst (by Mu Sigma) within a year of joining.
Received two Spot Awards by Mu Sigma
Nov 2012: For the Generalized Linear Modelling package.
May 2012: For individual contribution to Allstate’s big data project.
📆 2011-12-15 to 2013-06-25
I was a business intern for six months. My job was to get hands-on experience with software development for the banking industry. I developed certain statistical modules in Java 6 for an in-house “Banking Development Toolkit” called PRISM.
🏢 Oracle Financial Services Software Limited
📆 2011-07-04 to 2011-12-14