Preston VIC, Australia
Phone: xxx-xxx-xxxx
Email: xxx@xxxx.xxx
Looking For: Big Data, Data Scientist
Occupation: IT and Math
Degree: Doctoral Degree
Career Level: Fully Competent
Languages: English - Fluent
Highlights:
Skills:Big Data, Machine Learning, Artificial Intelligence
Big Data Engineer 8/2018 - 10/2018
Telstra, Melbourne, Victoria Australia
Industry: IT and Telecommunication
Our objective was to develop a NBN Service Performance tool to be used for analysis of network faults
Collaborated in the design of ingestion application of the company from S3 source files to Hive tables (PySpark, Hive)--
Big Data Developer 3/2017 - 7/2018
VORAC Artificial Intelligence, Perth, Western Australia Australia
Industry: IT
VORAC Artificial Intelligence, Perth, Australia
Our objective was to develop real time scalable machine learning prediction models on time series data to predict equipments’ failures for oil and gas refineries
+ Design and development of the ingestion application of the company to ingest and aggregate massive amount of sensor data from CSV files to HBase in real time by using Nifi, Spark Streaming, Kafka, and HBase
+ Developed various custom aggregation functions by using UDF functions in Spark to be used in ingestion application or machine learning models
+ Developed the Kafka offset handler of ingestion application to save Kafka offsets in HBase upon the restart of the ingestion application
+ Developed and designed the company HBase , Phoenix, and Cassandra tables and worked with their various Spark connectors (Spark Cassandra, Spark-Phoenix, and Spark HBase Connector - SHC) inside Spark
+ Employed pre-splitting algorithms on HBase tables for increased efficiency
+ Contributed to the design of the Nifi template for ingestion of different sources of CSV source files to Kafka
+ Used Livy client to run Spark jobs from Java applications
+ Developed prediction models by using various machine learning algorithms such as Random Forest, Decision Tree, Logistic and Linear Regressions, and Recurrent and Deep Neural Networks in different frameworks such as Spark ML, H2O, and Dl4j (Spark, Java, Livy)
+ Used R’ ARIMAx algorithm inside Spark to predict n-sample ahead of time-series data (R, Spark, Java)--
Big Data Developer 7/2016 - 1/2017
Cellos Software, Melbourne, Victoria Australia
Industry: IT and Telecommunication
My objective was to develop a Revenue Assurance (RA) system by using spark streaming. The system aimed to obtain the differences between customer usage across billing or network data nodes.
+ Developed a producer part of RA application to ingest CSV files to Kafka
+ Developed a consumer part of the application to consume the data from Kafka and then implemented the logic for the RA system
+ Involved in design of several HBase tables of the application--
Shahid Beheshti University 3/2002 - 1/2008
Tehran, Tehran, Iran
Degree: Bachelor's Degree
Major:Computer Sciense
Minor:Software Engineering
I finished my bachelor in software engineering in he fifth highest ranked university in Iran. My rank in national university entrance exam was 927 among around 500,000 participants to do my bachelor in one of top ranked universities in Iran.
Login to view resume: Mahdi Bazarganigilani -