Jul 2021 – Mar 2025 · 3 yrs 8 mos · Sunnyvale, California, United States

• I developed and owned a central monitoring system for several on-premise infrastructure clusters, using the open source Thanos framework. This involved bringing up the Thanos data consumer cluster using ArgoCD workflows and setting up Thanos on various data producer clusters for aggregation and querying of metrics.
• I maintained and supported an internal cloud based microservice to provide development infrastructure as a service, and contributed to scaling it up to support 200+ developers across various teams in Juniper’s CTO Organization.
• I contributed to and shipped a tool to assist with debugging customer deployments of Juniper’s Contrail networking product. I owned this tool’s feature test suite to identify regressions with feature development.

Feb 2021 – May 2021 · 3 mos · Pittsburgh, Pennsylvania, United States

• TA for 18-667, Algorithms for Large-scale Distributed Machine Learning and Optimization under Prof. Gauri Joshi.
• Course website: https://www.andrew.cmu.edu/course/18-667/

May 2020 – Aug 2020 · 3 mos · Pittsburgh, Pennsylvania, United States

• Developed a method to classify abnormal ciliary motion, using two-stream convolutional neural networks. Obtained a marginal improvement on the current benchmark performance for binary classification.
• Contributed to ManufacturingNet, an open source Python library offering robust implementations of featurization and learning algorithms to solve data-driven problems in the manufacturing industry. Accepted to NeurIPS 2020’s workshop on Machine Learning for Engineering Modelling, Simulation, and Design.
• Paper: https://ml4eng.github.io/camera_readys/52.pdf
• Library documentation: http://www.manufacturingnet.io/
• Advisor: Prof. Amir Barati Farimani

Jul 2019 – Dec 2019 · 5 mos · Bengaluru Area, India

• Implemented a novel approach for data-free deep learning using knowledge distillation for object detection.
• Built a baseline model to generate an object detection dataset from a trained model’s weights, for the Pascal dataset. The dataset was then used to distill knowledge from a larger model to a smaller model.

Jan 2019 – May 2019 · 4 mos · Singapore

• Introduced a deep learning based approach to recaptured video detection, using data created internally.
• Automated part of the dataset creation process in the lab, and extended existing work done for recaptured image detection to videos on the created dataset.
• Advisor: Prof. Alex C Kot

May 2018 – Jul 2018 · 2 mos · John F Welch Technology Centre, Bengaluru, Karnataka, India

• Worked with the Digital Solutions and Services team of GE Aviation at the John F Welch Technology Centre, Bangalore.
• Implemented projects that leveraged data science, process mining, natural language processing and data visualization for GE Aviation's manufacturing and engineering operations.
• Was given the opportunity to present my work at the Elevator Series, an open forum within GE that discusses technical approaches and solutions to various problem statements in the industry.