Engineer Data

SAINATH PALLA http://www.linkedin.com/in/sainathpalla

*** **** **, *** *** • Hartford, CT - 06106 • 717-***-**** • *******.*****@*****.***

EDUCATION:

University of Connecticut School of Business Hartford, CT

MS in Business Analytics and Project Management, GPA: 3.6/4.0 Jul 2016 (expected)

Relevant Coursework: Predictive Modelling, Big Data and Strategic Marketing

Padmasri Dr. B.V.Raju Institute of Technology TS, IND

Bachelor of Science in Computers, GPA: 3.5/4.0 2005 - 2009

Implemented a project on Image Thinning as part of Pattern Recognition Algorithm.

Skills:

Specialities: Spark, Hadoop ecosystem, SQL, Machine Learning, D3.js, NLP, Data Visualization

Programming & Tools: Scala, Java, Python, R, PIG, Hive, Tableau, Map Reduce, JMP

EXPERIENCE:

Research Assistant, University of Connecticut (Spring’ 16)

3D Image Recognition, using Apache Spark.

The research is divided into two parts, 3D Image fusion and 3D Image recognition.

Currently, I am assisting my professor in implementing 3D Image fusion and recognition algorithms in Spark.

Big Data Consultant, Infosys Limited- Analytics COE(Center of Excellence) Dec 2014 – Jul 2015

Daimler – Germany, real time streaming analysis of production machines using Apache Spark, Elastic Search, Kibana

Loaded real time data from logs of 5000 manufacturing machines equipped with sensors using kafka into Spark.

Performed SQL and window operations on data to identify defective machines, improved throughput time by 19%.

Stored data into elastic search server and displayed real time visualizations of machine performance on Kibana.

Predicted time to failure of machines with the sensor data and sending alerts for quick action as a POC.

Airtel – INDIA, data analysis of customers and billions of transactions to improve network quality and support broadband.

Configured data pipeline using Flume to capture billions of transactional data stored in form of logs and load into HDFS system. Accessed it through Apache Spark, preprocessed the raw data into meaningful dataset using Scala.

Performed analysis on the data using Spark SQL, identified internet usage patterns in different locations and used this data to improve its cable broadband subsidiary. This lead to 30% more subscriptions in tested areas.

Optimized the cellular towers and boosted the efficiency of networks by analyzing data usage patterns.

Built a model using Spark mllib to predict churn and network outage by analyzing the data from cellular towers.

Implemented a POC to Identify call dropouts by using Spark streaming for real time analysis of towers.

Data Engineer, Infosys Labs, Analytics CoE(Center of Excellence) Jan 2013 – Nov 2014

Accomplished a project for a major mineral mining company on Working Capital Optimization, used Spark Scala and Spark SQL. Showed an optimization of USD 40 Million by analyzing their millions of records. Also helped them in finding few of their vendors who are practicing fraudulent activities.

Led a team of 4 members for the development of a prototype of Scientific Literature text mining for drug repurposability for a leading American Pharmaceutical corporation using R, also worked on text classification using Naïve Bayes theorem.

Worked on integration of R with Hadoop ecosystem using packages such as RHadoop, SparkR. Also reprogrammed several algorithms in R to fit into this system.

Senior Systems Engineer Jan 2012 – Dec 2012

Worked on Hadoop and wrote several map reduce jobs to analyze millions of transactions of a leading Automobile manufacturing company, to provide useful statistical insights of their Sales and Distribution Data.

Systems Engineer Jan 2010 – Dec 2011

Worked as SAP CRM Technical Consultant in Infosys internal project.

Developed programs in ABAP for workflows, WebUI, report programs.

Trained new joiners on SAP as part of Infosys SAP training program.

Contact this candidate