● Part of the Product Development Division responsible for providing daily order proposals for retail stores across 13 customers in 7 timezones.● Designed and Implemented an Ingestion pipeline to ingest ML predictions using pre-caching techniques for fast API response time.● Integrated ML Algorithms with existing UIs to allow for manual override of ML Predictions● Parallelized Machine Learning algorithms and reporting tools using Dask Distributed Computingwith 750+ partitions for 500 million records daily.● Responsible for major design-level decisions with respect to improvements and technical debt indata ingestion and UI functionality.● Re-designed entire backend service architecture to decouple from other products/services andachieve 2x improvement in team efficiency.● Serve as point of contact to Product Leads and Product Management for planning, escalations,requirement gathering, product-related clarifications, etc.● Implemented clustering logic to improve ML pipeline run-time by 30%.● Led the CI/CD migration from InHouse Jenkins to Azure Based Service.● Implemented Intra Day Sales Feature to improve prediction quality of our ML Algorithms.● Took 100+ interviews for the role of Junior Data Analyst, Data Scientist, Junior Software Engineer,and Senior Software Engineer● Awarded Promotion and multiple spot awards

● Built an end-to-end data science pipeline reducing time spent per RFP● Achieved ~85% recall rate in extracting questions and answers from RFPs (in PDF, Doc, and Docx).● Developed a keyword extraction pipeline for questions by taking inspiration from a research paper.● Implemented Latent Semantic Indexing to return similar questions for a given question. Achieved state-of-the-art results post-fine-tuning for the business domain.● Awarded Rising Star (10K cash prize) for the year 2018● Developed a keyword extraction pipeline for questions by taking inspiration from a research paper.

● Designed a machine learning model (using Keras​ ) to identify any duplicate records in a dataset● Applied three distance metrics to create a 15-dimensional vector and found the optimum probability (98.2%) to classify as a duplicate● Achieved 9​9.99+% accuracy​ and presented to multiple clients including senior director of ​ fortune 100 company

• Taught data analysis on SPSS, Excel and RStudio as Teacher’s Assistant in ”BusinessStatistics” to E-MBA students at Delhi Technological University• Developed 7 data mining codes as an alternative to Nvivo (a paid software) usingR packages tm, ggplot2, wordcloud, treemap, tidytext, dplyr and stringrProject: Modelled an inventory sharing strategy and simulated it’s effectiveness on RStudio ( See Projects for details)

- Saved 250+ man hours in company's effort to expand it's vendor baseInitiated business in 30 of 36 cities alloted- Took initiative to travel to different cities where a telephonic conversation was not sufficient- Acquired TravelKhana's first brand restaurant(Sagar Ratna) since it's policy change 8 months prior to my joining

-Led a team of 32 members to conduct Workshops and CSR campaigns throughout the year- Achieved unprecedented profit margins (53% | 10 point increament YOY) and budgeted profits (INR 4,20,000 | 28% increase YOY)- Got Dr. Kiran Bedi on board as Quark's first ever brand ambassador- Conducted national workshop providing added revenue of INR 1,20,000