Big data analyst

AJITH K J

Big Data analyst

*.* years of IT experience in development of Big Data and Data Science applications using Hadoop Eco System, AWS cloud services. Experience in designing and developing Data pipelines (ETLs) using Pyspark.

****.*****@*****.***

812-***-****

Banglaore

linkedin.com/in/ajith-kj-ajith-

899a52136

github.com/ajithkjajith

SKILLS

Python

Java, RestFul Webservice

Hive, Sqoop, Oozie

Hadoop, Map Reduce

Spark SQL, Spark Streaming

Presto

AWS, EMR, RDS

TinyML

NLP, ML models

LANGUAGES

English

Professional Working Proficiency

Kannada

Professional Working Proficiency

Hindi

Limited Working Proficiency

INTERESTS

Writing Exams to blind

People as Scribe.

Playing keyboard

Work on new

technologies to bring up

optimal solutions to the

problem

EDUCATION

M.E in Big Data and Data Analytics 9.75/10

Manipal School of Information Science, Manipal

07/2019 - 05/2021,

B.E in Computer Science 8.7/10

The National Institute of Engineering, Mysuru

08/2013 - 07/2017,

WORK EXPERIENCE

Big Data and Data analyst intern (8 months)

Beckman Coulter

07/2020 - Present,

Responsible for Ingesting data using sqoop from traditional RDBMS database to AWS S3. Responsible for Writing ETLs using Hive and Hive Query Language. Developed Data Ingestion and Data Processing platform in spark. Worked on developing Restful APIs.

Responsible for monitoring and maintaining Data Quality. Associate Application developer (1.8 years)

Accenture solution private limited

11/2017 - 06/2019,

Developed ingestion framework to sqoop data from mainframes to extract information about the policies.

Creating Restful Webservices using jersey, springmvc, maven project. PERSONAL PROJECTS

Clinical prediction for dysphagia disorder using edge computing(tinyML)

(12/2020 - 03/2021)

Predicting early stage of dysphagia disorder in a patient using accelerometer and microphone data of swallowing different types of liquid.

Building tensorflow lite model which is capable of deploying machine learning models on aurdino board. Insights on covid-19 cases (07/2020 - 10/2020)

Scrapped covid-19 cases data from different offical websites using NLP. Data Exploration and pre-processing using various statistical analysis. Created various analytical reports to showcase the different dimension of increasing cases. Predicting Sepsis using Correlation Based Clustering of Patient Features

(08/2019 - 01/2020)

The main aim of this project is to derive an optimal set of patient features using correlation based clustering for sepsis prediction in adults.

Appropriate correlation measures (Pearson, Correlation ratio, Cramer’s V) are used to correlate mixed data type features.

Worked on highly imbalanced data set to bring optimal solution and improve model accuracy. Assessing Road Quality Using Unsupervised Machine Learning Techniques

(01/2021 - 04/2021)

Assessing road quality where road segments are unevenly paved, have potholes, and speed bumps. Unsupervised clustering allows data to speak for itself paving way for more sophisticated supervised learning approaches to aid in making policy decisions. Achievements/Tasks

Achievements/Tasks

Contact this candidate