Navneet Kapur's Email Addresses & Phone Numbers

📖 Summary

Staff Relevance Engineer @ LinkedIn Involved in Educational Content Discovery platforms at LinkedIn. These involve targeting users with educational content, more specifically Slideshare slides and Lynda courses, relevant to their job and career aspirations. From June 2015 to July 2015 (2 months) Mountain View, CAData Scientist Engineer @ Lyra Health Wore multiple hats working on the data back end ranging from data acquisition, preparation, standardization and modeling. 1. Consolidated Medical Provider Search Back-endBuilt out a crucial identity resolution module to consolidate information from multiple websites and build rich profiles for ~550,000 health providers in the US. Achieved high rates of recall and near-perfect precision (>99%) in doing so. • Built the required Elasticsearch indexers using their Java API and data standardization pieces to make the data mentioned above available for retrieval and analysis. • Made available to the rest of the team as part of an ingestion / standardization library. 2. Modeling Platform Built a classification / regression machine learning platform used as an R package internally. Developed a simple yet powerful JSON-based DSL for the specifying modeling parameters. • An input (referred to as a "model context") was provided in the form of a config file. The config specified preprocessing steps, independent variables, dependent variables, train/test splits, variable transformations, regularization and other parameters. Sensible defaults were used. • The output comprised trained parameters for a library of off-the-shelf machine learning algorithms and recommended which ones to use based on a loss matrix. These results and auto-generated graphs were versioned and snapshotted. 3. Used the modeling platform above for various set of cohorts and contexts to predict risk of behavioral health conditions based on responses to screeners and questionnaires. 4. Adaptive On-boarding ServiceArchitected and built the back-end rest service for an adaptive on-boarding flow responsive to inputs from users to allow effective matching to the best mental health providers based on the user's explicit needs and implicit diagnostic predictions. From July 2015 to May 2016 (11 months) Sr. Data Scientist @ LinkedIn I've been hard at work solving hard engineering and data science problems while building up the higher education data ecosystem at LinkedIn. The work can largely be divided into two logical pieces.1. Standardization Understanding and structuring data is key to its use in building awesome data products. A lot of the initial work involved standardizing schools, degrees and fields of study on profile. I built and shipped LinkedIn's near real-time school standardizer and shipped significant improvements to its existing degree and field of study standardizers at the time. There have been many iterations on these since.2. Building Awesome Data Products Once the data is structured, we can get our hands dirty with data! Over the years, I have worked on improving and scaling Similar Schools, shipping Notable Alumni and University Rankings - both for Graduate and Undergraduate degree levels. Check our blog on the methodology for LinkedIn University Rankings. http://blog.linkedin.com/2014/10/01/ranking-universities-based-on-career-outcomes/ From July 2012 to June 2015 (3 years) Mountain View, CASoftware Development Intern @ Google Worked on duplicate page detection for Graphic-rich pages. • Experimented with various approaches for image-matching and image-pair classification. • Using Surf descriptors, achieved high recall values for near-perfect precision. From July 2011 to September 2011 (3 months) Mountain View, CASummer Intern @ TU Ilmenau Worked on a graphical plugin for direct simulations in MLDesigner - a hierarchical simulation modeling tool. From May 2008 to July 2008 (3 months) Research Assistant @ Stanford University Was part of the Societal Networks team under Prof. Balaji Prabhakar on projects involving social incentivizing schemes - Insinc and Capri. • Worked on the back-end and front-end for the website platforms for the programs• Part of the 2-person team which conceptualized and implemented the point-redemption pieces (included a social board-game) which are a core part of the user experience. From October 2011 to June 2012 (9 months) StanfordHead of Data @ GoFundMe From June 2018 to June 2019 (1 year 1 month) San Francisco Bay AreaSenior Staff Software Engineer, Data and Relevance Engineering @ GoFundMe From January 2018 to June 2018 (6 months) San Francisco Bay AreaSoftware Engineering Lead on Data @ GoFundMe Working on data products to empower philanthropy! From June 2016 to January 2018 (1 year 8 months) San Francisco Bay AreaDevelopment Intern @ Bell Labs. Research India Worked on a mobile networking and social-sharing app, "MANGO". From May 2009 to July 2009 (3 months) Head of Core and Data Platforms @ GoFundMe