Karan Thacker Email & Phone Number

Sunnyvale, Ca, Us

Austin, Texas, United States

Cupertino, California, United States

• Carried out literature survey on Deep Learning Models for Image Segmentation and object classification models, aimed at automating image editing tasks for Apple Media Products• Built a Text Segmentation Network by applying concepts of attention mechanism and transfer learning, silhouetting non-convex boundaries and diverse textures in the image• Researched, implemented, and evaluated a variety of published approaches for image processing• Pruned and compressed Machine Learning models, improving prediction inference time and further reducing cloud computing resources. • Containerized and deployed trained models on cloud using AWS, creating a RESTful API, making the model available to be integrated as a micro-service• Developed Image Inpainting Service which regenerating cropped parts in an image, using GANs

Bengaluru, Karnataka, India

• Automated selection and ranking of bio-medical/clinical documents for medicinal research using NLP models (spaCy, scispaCy) specializing in scientific text data, leading to 90%+ reduction of man hours spent on screening documents• Created data pre-processing and training pipeline on cloud ML infrastructure (AWS SageMaker), including tokenizing and vectorizing of text data• Deployed the ML inference pipeline on cloud, as containerized microservice application with Flask as the web framework

Interacting with students enrolled in Data Science courses from all around the world, helping them with coding challenges (R/Python) and statistical concepts (Hypothesis Testing, Measures of central tendency).Frequently hosting Webinars and Video calls on discussions with students.

Pune Area, India

• Performed Data Migration and Remediation of Manufacturing Data, implemented QA automation and data analysis, leading to creation of optimized and fault tolerant data models for client• Built and maintained web applications using MERN stack• Analyzed and refactored legacy code, leading to reduction of technical debt and streamlining of data transformation pipeline• Performed Data Migration and Remediation of Manufacturing Data in PostgreSQL, implemented QA automation and ETL pipeline using Python and Spark on Elastic MapReduce Cluster, leading to creation of robust, optimized and fault tolerant data models for client • Created ML POCs for customer churn and fraud detection using Tree Classifiers and Clustering Algorithms

Ahmedabad, Gujarat, India

Master'S Degree, Computer Science

Bachelor Of Technology, Electronics And Communications Engineering