Livanshu Kashyap

Data Science/Machine learning/Cloud Computing

  Mississauga, ON              linkedin.com/in/livanshu               [email protected]            437-986-2206

Professional Summary:

  • 2+ years of hands-on experience in developing Machine Learning and Deep Learning models for clustering, regression and classification solutions using Python programming language. 
  • Experience with structured as well as unstructured data like images to perform tasks like image classification,  augmentation, dropout, object detection, etc with CNN's and text data to perform tasks like tokenization, embeddings, projection, translation, NER, sentiment analysis, chatbots etc. on frameworks like TensorFlow.
  • In depth knowledge of modern as well as conventional machine learning algorithms like XGBoost, kNN, linear/logistic regression, k-means, Naive Bayes, SVM, Random-forest, Decision trees, PCA etc. with knowledge of specifications of data preprocessing and fine-tuning hyperparameters for these algorithms. 
  • Build ETL/ELT and Data pipelines for streaming as well as batch data using Apache Airflow & Kafka and can design a complete data warehouse with star/snowflake schema using fact/dimension tables with data loading, data verification, change detection and visual dashboard (Cognos) as well as applying CUBE and ROLLUP options.
  • Hands-on experience with setting up different databases and performing SQL queries for data retrieval and transformation, as well as processes like data analysis, data cleaning, feature engineering and data transformation. Can handle different datatypes, filetypes and encodings.
  • Extensive experience in transfer learning and fine-tuning using TensorFlow Hub, Keras retrained models and Sagemaker Docker Images. Certified in cloud computing and can perform all the above processes on the cloud: 2X AWSUnderstanding of agile methodology and its values: Certified in Google Agile Project Management.

Technical Summary:

  • Programming:                                                   Python, SQL
  • Frameworks:                                                     TensorFlow, Keras, sklearn, Spark(MLlib)
  • Databases:                                                        MySQL, PostgreSQL, DB2, S3, Aurora
  • Text/Images:                                                     Spacy, NLTK, Pandas, Numpy
  • Visualization:                                                    Matplotlib, Seaborn, Tableau, Cognos, QuickSight
  • Cloud:                                                    Amazon Web Services, Google Cloud Platform

Professional Certifications:

   Machine Learning Specialty      Cloud Practitioner      TensorFlow Certified Developer      MySQL      Google Agile Project Management      IBM - SQL for Data Science      Tableau      IBM - ETL & Data Warehousing     

Education:

McMaster University  Hamilton, ON    MEng.   GPA 3.5    Awarded Nov 2020 

Courses: Artificial Intelligence; Multivariate Big Data Analysis; Systems Modelling & Optimization; Machine Learning Classification models; Manufacturing Systems; Sustainable Man. Processes. 

Thapar University  Patiala, India    BEng.   Mechatronics    GPA 3.7  • Awarded Jul 2019

Courses: Data Structures; Artificial Intelligence; Statistical Methods and Algorithms; Pattern Recognition and Image Processing; Digital Signal Processing.

Projects:

  • Text Classification of insincere questions on Quora by Fine-tuning BERT on top of TensorFlow
    • EDA and Feature Engineering 
    • TensorFlow Pipeline with multiple inputs
    • Preprocess and Tokenizing
    • Fine-tuning BERT model
    • Evaluation
  • Image classification using different modern models on top of TensorFlow on the VOC dataset 
    • Transfer learning: ResNet50, MobileNet, AlexNet and VGG
    • Learning rate optimization
  • Complete business solution for Legalist Inc. to predict outcome of federal cases
    • Multiple ML models, including clustering, regression and classification for US Federal cases dataset
    • In depth data wrangling and feature engineering
    • Model tuning and evaluation
  • Toll Traffic streaming data ETL simulation using Apache Kafka and Apache Airflow
    • Kafka Server: Zookeeper, Topic creation and streaming live data from simulator to MySQL database
    • Developing, monitoring and logging DAG's
  • Deployment of ML model of Spam detector on AWS Cloud Servers using AWS Elastic Beanstalk
    • Flask RESTful API - GET/POST
    • AWS Elastic Beanstalk: Application versioning, Server logs, Server performance monitoring & terminating

Work Experience:

DeepPixel Inc. - Toronto, ON    Data Engineering (Intern)   Apr 2021  - Sep 2021 

LG Electronics - India  •  Co-op • Jan 2018 – Jul 2018

Exicom Tele-systems Ltd. - India  •  QA Engineer •  Aug 2014 – Jan 2016 


Date:   03-Jan-2022                                                        

                                                        Livanshu Kashyap