Shameer Warulkar

Experience

• 

  IFTA

  Nov 2014 - May 2015

  Software Engineer

  - Web ETL system- Document clustering

• 

  Cubictree Technology Solutions Pvt Ltd

  May 2015 - Dec 2016

  Data Scientist

  - Distributed and scalable ETL Engine extracting and processing data from over 75000+ data sources. - Generic self-learning website politeness module for intelligent web crawling.- Data Sanitization of crawled data by applying NLP techniques.- Dash-boarding entire business process to be utilized by multiple stakeholders.- Cloud infrastructure management and its continuous optimization.

• 

  Securly

  Jan 2017 - Feb 2020

  Implemented a profiler system capable of analyzing students’ online behavior on various platforms, enabling experts to respond to potential threats with informed decisions based on accurate threat assessments.Search classifier, categorizes search queries from various sources. This uses a hybrid of db lookups, domain analysis and web page content analysis.Feature Engineering, work closely with a team of psychologists and studenty safety experts to understand various types of child behavior and issues. Term and phrase context analysis based on model feature weights for fine-tuning training data and parameters of the model to be better at handling child vocabulary subtleties and trends. Utilize this feature knowledge for analysis of the classification models for root cause analysis of a particular classification. Show less Led the development of robust intent classifiers to analyze over 10M multilingual conversations and documents daily to detect bullying, suicidal and other harmful activities with high accuracy. Continuously enhanced performance metrics by exploring advanced preprocessing, representation, and classification techniques.Pagescan, a content-based dynamic domain categorization system to determine if its safe to be accessed by minors. This decision is made by analyzing textual and image data available on the domain. Pagescan categorizes domain into pornography, gambling, social media and proxy. Show less

  • Sr. Data Scientist

    Jul 2019 - Feb 2020

  • Data Scientist

    Jan 2017 - Jul 2019
• 

  Rho AI

  Feb 2020 - Dec 2020

  Sr. Data Scientist

  Research and POCs for NER over webpages

• 

  Forage AI

  Jan 2021 - Feb 2022

  Sr. Data Scientist

  Generic Web Profiler - Added intelligence to in-house large scale web crawlers giving them the ability to identify named entities and creating relations between them. These entities and relations were utilized by biggest players in financial and medical domains.

• 

  Syte

  Mar 2022 - Dec 2022

  Data Scientist

  • Text Search, conducted research over millions of search queries revealing many improvements for matching, ranking and suggestions for client inventory and better product discovery.• Recommendations engine, serving biggest international players in fashion, home decor and jewellery. • Multi-Lingual item classifier

• 

  Revuze

  Aug 2023 - now

  Sr. Data Engineer