Barclays, New York
Technology Analyst, July 2020 - Present
Hudson and Thames Quantitative Research, New York
Head of Research - Portfolio Optimisation, July 2019 - Present
This is a quantitative finance research group focused on implementing academic research in buy-side investment management. Because of a very high barrier for entry in quant finance, our aim is to create open-source implementations and make it available for everyone to learn from and enter the field.
As a head of research and co-author of Hudson and Thame’s open-source Python package - mlfinlab, I lead the development of its portfolio optimisation module. Most of my time is spent reading research papers from academic journals, collaborating with professors and researchers from around the world and writing production quality code.
FOR.ai, New York
Machine Learning Researcher, July 2019 - November 2019
For.ai is a distributed research group where the idea is to extend the current state-of-the-art research in machine learning and deep learning. The hope is to make a valuable contribution to the field in the form of good quality research papers.
As a researcher, I am doing research on curiosity-driven reinforcement learning agents and trying to improve upon Google’s current research in it.
Barclays, New York
Software Developer Intern, June 2019 - Aug 2019
I was part of the equities trading support team and helped in setting up a new trading monitoring system - the ITRS Geneos tool. The idea is to create a monitoring system for the traders which constantly monitors the health of the applications and is intelligent enough to detect issues and bottlenecks in the system.
Apteo, New York
Data Scientist, August 2017 - August 2018
Apteo is a fintech startup based in Manhattan, New York in the Flatiron neighborhood. I was a remote intern from India and helped them develop their AI powered trading product - Milton. Over the course of 1 year I worked on diverse tasks:
Developing an automated trading agent using deep reinforcement learning for executing optimal trading strategies.
Use financial text articles to generate document vectors (doc2vec) and improve neural network accuracy in predicting stock returns.
Integrating different financial features into Milton. These features are a combination of company fundamentals data and features extracted from financial articles.
DAIICT, Gandhinagar
Teaching Assistant, January 2018 - April 2018
Under the guidance of Prof. Jaideep Mulherkar, I was in charge of developing assignments and lab material for Computational Finance (CS401) - a course based on the computational aspects and mathematical aspects of the stockmarket. I developed and graded 60 Computational Science students’ weekly python lab assignments spanning varied topics:
Binomial Asset Pricing
Risk Free Arbitrage
Monte Carlo Theorem
Black Scholes Equation
Playpower Labs, Gandhinagar
Data Science Intern, September 2017 - November 2017
Playpower labs is an education company developing educational content. My task was to analyze student educational data and gain insights into factors which affect the scholastic performance of students - fluency, speech, endurance and teaching methodology in the schools.
Shipmnts, Ahmedabad
Machine Learning Intern, May 2017 - July 2017
This was my first machine learning internship and it was a really cool one. Being a shipping logistics company, the data was mostly shipping documents, invoices, images and PDFs. Naturally, my projects at Shipmnts were related to document processing and extracting information from them:
Image and PDF enhancement using OpenCV for efficient image processing.
Detect repeated structures in an image from a single annotated instance of the record. The information is extracted with 90% accuracy using Fuzzy similarities, visual and semantic heuristics.
Detection of table headers in images and documents using machine learning.
