Jan 2023 – Apr 2024 · 1 yr 3 mos · Bengaluru, Karnataka, India

• Quantitative Research Development - Portfolio Implementation & Optimization

Dec 2021 – Jan 2023 · 1 yr 1 mo · Bengaluru, Karnataka, India

• Quantitative Research Development - Portfolio Implementation & Optimization

Oct 2020 – Dec 2021 · 1 yr 2 mos

Jun 2019 – Sep 2020 · 1 yr 3 mos

Jul 2019 – Dec 2021 · 2 yrs 5 mos · Greater Bengaluru Area · On-site

• Worked as a Full-Stack developer at Morgan Stanley with Client-Docs project, which facilitates client-onboarding.
• Developed a web project using Angular to simplify client onboarding process. Also worked on integrating usage tracker for the whole application, which helped the business to understand the application usage patterns of the users.
• Designed and developed RESTful APIs using Spring JDBC template and Spring Boot for various features.
• Worked on creating MQ connection using JMS, to publish/subscribe on events sent/received from other system.
• Worked on creating a Perl script to ease the update on various datapoints for the provided large set of documents.
• Participated in full SDLC – from designing and coding through system testing, integration and deployment

May 2018 – Jul 2018 · 2 mos · Bengaluru, Karnataka, India

• As a part of Data Science team of StackRoute I worked on enhancing the functionality of an open source project: Machine Learning Workbench (MLWB); this would allow deployment of machine learning pipeline infrastructure in a distributed fashion.
• MLWB is basically an abstraction of Machine Learning (ML) solutions as editable computational graphs composed of reusable ML tasks. This is basically used by the data scientists for rapid experimentation.
• Provided a scalable and flexible solution to the MLWB using containerization and orchestration tools available in the market.
• Technologies worked with:
• Docker: for the containerization of the machine learning pipeline.
• Apache-airflow: for the orchestration of different nodes of the machine learning pipeline.
• Kubernetes: used k8s as a container management tool. which automates container deployment, container (de)scaling and container load balancing
• AWS: deployed the containers on the EC2 instances.

Dec 2017 – Jan 2018 · 1 mo · Gurugram, Haryana, India

• Project: "Customer Churn Prediction".
• Churn prediction consists of detecting which customers are likely to cancel a subscription to a service based on how they use the service.
• Used a dataset containing 20000 subscribers and observed that a combination of logistic regression
• and perceptron algorithm gave the best results.
• Used a dataset of 33333 customers and used neural networks, SVMs and Bayesian networks for
• predictive modelling. The results of experiments indicated that neural network based approach
• can predict customer churn with accuracy more than 92%.