Developed an end-to-end application for scraping scanned images of handwritten mails from an internal website and extracting data from it.

Used AWS Textract and OpenAl along with Donut model to do OCR of handwritten images and extract information in a structured format.

Implemented a web scraping solution using Selenium and Beautiful Soup.

Built a heuristic algorithm to identify and extract relevant information and amendments from policy documents published by US federal agencies.

Used LLMs to make amendments into federal regulations based on published policy by multiple federal agencies.

Built a front-end application using Streamlit to compare changes in regulation.

Developed an end-to-end recommendation engine for a platform that sells raw materials to restaurants.

Scraped restaurant menus and used items in the menu to generate personalized recommendations for raw materials.

Deployed the recommendation engine as a service on AWS using AWS Lambda, DynamoDB, and Step Functions.

Developed automated moderation systems to streamline the review of more than 5 billion ads annually.

Led a team of three in enhancing current Machine Learning systems, cutting down the number of ads requiring manual moderation by 60%.

Achieved a $500 million annual reduction in shipping invoice estimation errors by training a gradient boosting machine (GBM) model using H2O to handle a large training dataset of 250 million samples.

Constructed a regression model designed to predict invoice amounts for more than 50 million third-party shipments per week.

Built a dispatch time optimizer for the Amazon India network to deliver 10% of shipments one day faster.

Used concepts of vehicle routing optimization and built a line-haul route planner tool for the Amazon line-haul network.

Created a workforce scheduling tool using constraint programming to automate and optimize human resources deployment at the Amazon sort center, which resulted in an 8% reduction in the workforce.

Utilized MILP formulation and lifted cutting plane techniques to reduce the runtime of post and parcel network scheduling optimization from 74 hours to just 30 seconds.

Designed a network simulation tool for assessing the speed impact on the network due to configuration changes.

Developed a state-of-the-art tool to solve vehicle routing problems with real-life constraints using heuristic algorithms.

Collaborated with global clients for topology and production planning optimization.

Developed a routing algorithm for solving ship container routing for a leading petrochemical producer.

Worked on network optimization problems to identify optimal supply chain network configuration for Indian and global clients using Llamasoft Supply Chain Guru and internally developed tools.

Performed oil vessel routing and scheduling optimization to identify opportunity to reduce logistic cost by 10%.

Helped an Indian chemical client reduce logistics cost by 11% through online bidding.