Vaishnavi Avinash Jamdade

LinkedIn GitHub adwo45@r.postjobfree.com Dallas, Texas-75234 +1-667-***-**** EDUCATION:

MASTERS OF SCIENCE, COMPUTER SCIENCE, G.P.A : 3.7/4.0 28 Aug 2019-25 May 2021 University of Maryland Baltimore County, United States. BACHELORS, COMPUTER ENGINEERING, G.P.A : 3.6/4.0 15 Aug 2014-15 May 2018 University of Pune, Maharashtra, India.

TECHNICAL SKILLS:

Programming: Python, Java, C++, Javascript, Typescript, HTML/CSS, Flask, AngularJS, NodeJS, React Databases: MySQL, AWS (S3, Lambda, DynamoDB, EC2), Oracle SQL, Teradata, SybaseIQ, PostgreSQL, Presto Development Tools & Methodologies: Git, Subversion (svn), JIRA, Maven, CI/CD, TeamCity, GitHub, GitLab, Terraform, Agile, Scrum, Kanban Libraries, Frameworks & Technologies: Docker, Rest API, sklearn, NumPy, Pandas, Matplotlib, Seaborn, Tensorflow, Keras, PyTorch, FastAI, RASA Operating Systems: Windows, Linux, Unix

Test & Test management Tools: Selenium WebDriver, UFT, HP-ALM, JUnit WORK EXPERIENCE:

Associate Software Engineer, Goldman Sachs, Dallas, Texas, US. 23 August 2021- Present

• Backend Developer and open-source contributor for Data Engineering division’s end-to-end Data Modeling Platform – FINOS Legend.

• Worked with data management products as a service (PaaS) and its migration to the new Legend platform. Built and tested seamless services through data modeling environment which supports proprietary programming language to perform model-to-model transformation to encourage data standardization, providing an abstraction layer for users by eliminating necessity of writing complex SQLs.

• Contributed to the transformation of end-to-end data-model queries to SQL queries by adding native support for significant functions to the Legend platform extending support to a multitude of relational databases, further allowing BI tool integration with Legend. Worked on testing the developed features in Java by writing Junit tests and on API development.

• Assisted in improving the proprietary language used for data modeling by developing new and missing features to ensure SQL uniformity.

• Onboarded and mentored team members and helped them with project walkthroughs, deliverables, and technical documentation. Guest Researcher, VIPAR Lab, University of Maryland Baltimore County, Maryland, US. 12 July 2021 – 21 Aug 2021

• Developed classification algorithms in Python for malignancy of lung nodules in CT scans for Explainable AI-assisted Lung Cancer screening.

• Prime focus included predicting multitude of fields to estimate malignancy as well as other correlated biomarker variables, performance evaluation of algorithm through presentation of accuracy malignancy screening, and many other comparable metrics for biomarker fields. Data Science & AI Intern, Atos zData Inc., Irving, Texas, US. 29 June 2020-28 Aug 2020

• Worked on a chatbot application that supports users with DACA immigration related queries and procedures.

• Designed and developed the NLU module to pull videos of lawyers answering immigration-related questions from relevant platforms like Facebook. This data was stored in Elasticsearch DB to facilitate fast queries.

• Implemented the NLU model for recommending videos relevant to user queries using the RASA framework. The application is being deployed in Amazon ECS.

Graduate Teaching Assistant (part-time), University of Maryland Baltimore County, Maryland, US. 28 Aug 2019-25 May 2021

• Assistant for course Principles of Operating Systems, Advanced Operating Systems, and Graphical User Interface Programming. Helped students with OS (Linux) and GUI queries, resolving the code in C++, HTML, CSS, JavaScript and Python.

• Assisted faculty member in grading assignments and exams, advising, proctoring, and administrative duties necessary for courses. Associate Software Engineer, Accenture, Pune, India. 22 Oct 2018-15 June 2019

• Responsible for Backend System Integration Testing of Enterprise Data Warehouse.

• Designed and implemented test cases based on ETL specification documents, use cases, low-level design documents.

• Execution and Analysis of test cases for a web application with the capability to track test defects and perform Regression and Progression Data Warehouse Testing. Developed scalable, reusable test automation scripts for boosting ETL test execution in Python. Machine Learning Intern, JobMosis Talent Solutions (now LitmusBlox), Pune, India. 19 July 2018-30 Sept 2018

• Design and developed a startup product, a chatbot application in Python to recommend job roles for candidates based on inputs from resume.

• Implemented feature extraction using data mining algorithms and performed classification.

• Adopted Agile methodologies and led tasks of requirements gathering, low-level design, and actively participated in daily Scrum meetings.

• Programmed a statistical analysis code in Python to aid and keep track of the performance of the model and provided alternate solutions. PROJECTS:

• Demand Forecasting as a service to aid technology-based choices using Stack Overflow data (Academic project Oct 2020): Designed a web application that allows users to review informative statistics and future trends in technology by aggregating and visualizing the crowdsourced knowledge of technologies from 30m stack overflow (SO) posts. Used BigQuery helper package to facilitate fast queries from BigQuery dataset. Implemented Prophet time-series forecasting model for predicting popularity index on basis of features of posts for every technology tag in Stack Overflow. Used Flask and Python for Backend and AngularJS and Bootstrap for Frontend. Application was deployed in AWS.

• Explainable Lung Nodule Malignancy Classification from CT scans (Master’s Thesis): Presented a novel approach for malignancy classification of lung nodules in CT scans for Explainable AI-assisted Lung Cancer screening. Employed a 3D(CNN) machine learning model in Python to predict the malignancy level and biomarker attributes. Uniquely predicted multitude of fields to estimate malignancy & other correlated biomarker variables. Evaluated the classification algorithm in several ways including presentation of accuracy and other comparable metrics for biomarker fields.

• Distributed Transaction Server (Academic project 2019): Implemented concurrency control between server and multiple clients using thread synchronization to handle multiple client requests by ensuring thread safety and data consistency. Incorporated mutexes to ensure thread safety. Developed code in C++ for implementing Berkeley Algorithm for clock synchronization.

Contact this candidate