Professional Documents
Culture Documents
Data Engineer
Summary
Innovative IT professional oering vast experience leveraging software engineering and Data Science
techniques and methodologies to deliver highly eective and creative solutions to business big-data
challenges. Has deep understanding of statistical and predictive modeling concepts, machine-learning
approaches, clustering and classication techniques, and recommendation and optimization
algorithms. Highly organized with strong capacity to prioritize workload and steer project completion within
established deadlines.
Core Competencies
Skills
HDFS / Hadoop
Hadoop 2.x, YARN, HDFS, MapReduce V2, Spark 2.x,
Pig, Hive, Oozie, Hue, Sqoop, Flume, ZooKeeper, Kafka, Storm, Spark
SQL, Spark MLib, Avro, Parquet, Ambari, Solr
Machine Learning
Binary Classification, Naive Bayes Classification, Linear & Logistic
Algorithms / Techniques
Regression, Decision trees, CART & Random forests, Text mining,
Predictive Analytics, Deep learning, Neural Networks, Support Vector
Machine, Collaborative filtering, Clustering
Languages
JAVA, Scala, Python
Hadoop Distribution
Cloudera, Hortonworks
Cloud Technologies
Amazon Web Services, Azure, Pivotal Cloud Foundry
Data Visualization
D3js, Spark Graphx, Apache Zeppelin, Tableau
https://www.visualcv.com/srinivasa-prasad
Databases
Oracle 10i/11g, MS SQL Server, HBase, Cassandra, Greenplum,
Mongo DB, Redis
Others
Rabbit MQ, Git, Maven, Jenkins, HTML5, CSS, Java Script, SOAP, REST
Work History
Build required statistical models and heuristics to predict, optimize, and guide various aspects of
organization's business based on available data.
Communicate the insights using effective visualization techniques and make appropriate
recommendations.
Utilizing highly attuned analytical skills to develop IT and business strategies employing cutting-edge
technologies to increase productivity.
Consistently drive high standards of service through effective project management, communication, and
strategic planning to develop and manage strong client relationships.
Work independently with Business units/Function SME to understand the business objective/challenges
and propose an analytical solution.
Key Projects / Initiatives
Migration of Pivotal HD 3.0.1 to Hadoop 2.3
Which involved Ambari, Hive, HBase in-place upgrade
Microsoft Exchange Server Analytics - Predictive solution to analyze the historical events and predict the
occurrence of critical events 30 minutes in advance
Rabbit MQ pulls all the log files and pushes to Spark HD through Spark Streaming for segregation
Then pushed to neural network model built on Theano Tensorflow, to analyze the pattern and
predict critical events.
All the events are stored in Greenplum DB for the Tensorflow to train the neural network model.
Security Analytics - User Behavior - predict user login anomalies over VPN
Rabbit MQ is used for real time streaming VPN user session logs, then Spark jobs to parse the log
files, and validate with historical data set (trained based on the user coordinates and login time in
the past), in case of anomaly inform the critical incident management team
Education
Certifications
https://www.visualcv.com/srinivasa-prasad