Experiences

Machine Learning Research Intern, Lenovo Research   –   June - August 2022

• Manager: Grant Lloyd, Executive Director, Lenovo Research, Mentor: John Nicholson, Principal Research, Lenovo Research.
• My tasks broadly encapsulate chanlleges to deal with Low Light Imaging conditions on Lenovo ThinkPads, Tablets, and Motorola smartphones.
• During my time, I was the dataset owner for the team. My duties included understanding dataset, organization, triaging, building histograms and implementation and training model.
• I implemented and trained a redesigned Low-Light Net model that served better for the Thinkpad use case.
• Performed data structuring for better model generalization to counter distritbution shifts.

Ph.D. Summer Intern, Lawrence Berkeley National Lab, ESnet   –   June - August 2021

(Won the Best Paper Award at SC21 - INDIS)

• Supervisor: Dr. Inder Monga, Mentor: Dr. Ezra Kissel
• Deployed a deep learning approach to automate the dynamic auto-tuning of pacing rate in DTNs
• Developed kernel level system & traffic control operations in DTNaaS docker container.
• Integrated a supporting tool that can dynamically visualize the elastic search data for real-time parameter optimization.

Peer Mentor, Lehigh University (NSF-REU) 2020 (CNS-1757787)  –   May - August 2020

• Mentoring and closely guiding 15 NSF-REU Interns on their respective site projects.
• Duties included: Weekly one-on-one discussions with each intern, understanding their fallouts and helping them out with their codes and other low level academic issues.

Research Assistant, Resilience Research Group for SARS-CoV-2  –   June - August 2020

• Supervisor: Dr. Brian D. Davison
• Image Gathering for face-masks in United States.
• Designing a novel face-mask detection algorithm for a survey research on SARS-CoV-2.
• Funded by Lehigh Research Grants and partially funded by (NSF-1841338)

Research Intern, Lawrence Berkeley National Lab, NERSC (link)  –   June - August 2019

• Supervisor: Dr. Brian Austin
• Developed scripts to fetch and analyze terabytes of data from the SLURM scheduler.
• Analyzed & estimated real-time queues in the scheduler for optimizing the policies for incoming jobs.
• Developed three real-time policies that potentially improved the allocation procedure.
  • Draining
  • Job Cancellation
  • Job Pausing

Machine Learning Intern, Persistent Systems ltd (link)  –   June - August 2017

• Developed a facial recognition and verification system using Google’s FaceNET research as the baseline.
• Added additional OpenCV features on top of it, which can differentiate between 3-D and 2-D images.
• Designed a purely browser-based RSA compliant module to work with FIDO keys.