Keep in touch with meI'm using Intch to connect with new people. Use this link to open chat with me via Intch app
Work Background
Persistent SystemsAcademic Intern
Jan. 2022 - Apr. 2022Mumbai, Maharashtra, India• Accelerated manual classification of cells in histopathological images, resulting in 80% increase in efficiency, by building Image Segmentation Models to detect and count different types of cells.
• Engineered pipeline to perform face-matching post-enhancement of government IDs and portrait photos using GANs.
• Enhanced accuracy by 15% and expedited preprocessing with 40% increase in speed to 3 seconds by streamlining the pipeline to incorporate Deep Learning model for keyword extraction on text, post speech-to-text conversion.
AkzoNobelData Science Intern
Aug. 2021 - Dec. 2021Netherlands• Improved accuracy of model by 20%, as measured by its ability to classify colors based on reflection values, by implementing ensemble of Random Forest and Light Gradient Boosting Models using Scikit-Learn.
• Simplified color recipe-generating process by building Machine Learning models to generate color recipes using solid colors.
• Rationalized relating colors and toners by analyzing large-scale color recipe datasets and performing ETL processes.
Kenmark ITan SolutionsJunior Data Science Associate
Apr. 2020 - Jul. 2020Mumbai Metropolitan Region• Led development of text-cleaning pipeline that reduced processing time by 40% to 7 seconds and expedited integration of data.
• Improved F1 Score by 30% using recurrent neural networks for sentiment analysis on Bert embeddings of cleaned comments.
• Conducted and facilitated knowledge transfer by hosting a tutoring session for 11 full-time staff members.
Sapio AnalyticsData Analyst Intern
Apr. 2020 - Jun. 2020Mumbai, Maharashtra, India• Maximized supply chain efficiency of delivering Covid-19 vaccines by designing and publishing a collaborative dashboard using Tableau and Dash, used AWS to extract key metrics. Presented it to the Andhra Pradesh government as a proposal.
• Analyzed historical data and market dynamics to predict need of essential supplies at hyper-granular level in India.
• Managed SQL database (over 40 tables 100,000 rows each) for COVID-19 Project, used by mobile and web applications.
Intch is a Professional Networking App for the Future of Work