Jan 2023 – Oct 2024 · 1 yr 9 mos

• Personalizing the user experience on Glance game center along with improving the user reach for the gaming platform
• Working on maximizing the per game revenue
• Built user acquisition model for Glance Real Money Gaming platform (HiScore) with the target of improving down the funnel metrics viz. depositor count, reducing the cost per depositor (CPD) and improving the M1 recovery rate.
• Developed LTV model using RFM technique for retaining high-value users on HiScore

Apr 2021 – Dec 2022 · 1 yr 8 mos

• Built the pipelines and models for ad optimization on the Glance surface that achieved ~40% improvement in CVM install and ~10% improvement in registration rate across the advertisers.
• Built a passive experimentation framework in order to compare the model performances before taking them live on A/B experimentation
• Worked on building deep learning based recommender models for personalizing the Glance feed
• Built metabase dashboards for monitoring the model performance

Jun 2020 – Mar 2021 · 9 mos

• Worked on onboarding a new product NSX-T onto Skyline.
• Worked on integrating vRealize Operations Cloud with Skyline.

Jul 2018 – Jun 2020 · 1 yr 11 mos

• Involved in building backend services for a customer-facing platform, Skyline, that helps VMware revolutionise its customer support from reactive to proactive.
• Worked on finding customer cohorts with the aim to personalise Skyline alerts and recommendations.
• Worked on the project ML Engine that involved building a common pipeline for all the ML tasks, right from preprocessing to deployment, so that the same ML model can be leveraged by different teams across VMware.

May 2017 – Jul 2017 · 2 mos · Bengaluru Area, India

• Implemented a deep learning encoder-decoder model to detect anomaly in firewall data using TensorLayer as a PoC.

Dec 2016 – Dec 2016 · 0 mo · Bengaluru Area, India

• Worked on automating the brain tumour (Glioblastomas) detection using MRI scans. It involved implementing an input cascaded Convolutional Neural Networks using two pathway architecture in order to detect both local and global features of the tumour.

May 2016 – Jul 2016 · 2 mos · Bengaluru Area, India

• Worked on the project Algorithmic music generation, that involved developing an LSTM model to generate plausible music on its own.
• Gave a talk proposal on the same which was among the 25 talk proposals that were accepted for presentation at PyCon India 2016, at New Delhi. Presented on 25th September 2016, received an encouraging response and ideas to work on further.
• Gave a talk on the improved version of the same project at PyCon 2017, Portland, USA on 19th May 2017. Being one of the very few student speakers, received an extremely positive response and ideas to work even further on this project.