Banner Image


  • Apache Spark
  • Big Data
  • Cassandra
  • Data Science
  • Elasticsearch
  • Hadoop
  • Hive
  • MongoDB
  • R Programming
  • Solr


  • Spark and Hadoop Expert

    $15/hr Starting at $100 Ongoing

    Dedicated Resource

    Architect responsible for driving the BigData and Analytics that maximize the pace of innovation with Development and Product. 5+ years hands on experience on various databases like Spark, Kafka, Hadoop,...

    Apache SparkBig DataCassandraData ScienceElasticsearch


Artificial Intelligence, Deep Learning, Hadoop, Spark, Scala, Elastic Search, Computer Vision, Kafka, NLP, Machine Learning Consultant

1.Worked for an end to end marketing product where drupal log files data is moved on a real-time basis using Kafka,Spark Streaming and ElasticSearch. Predictive analysis is done on the log files based on the website access to restrict access to bad bots/IP addresses using Collaborative Filtering.
a.Content Recommendation - for any given content, recommend the next most popular by association.
b.Identify Good and Bad Bots/IP and restrict on real-time basis.
c.The propensity to Repeat Purchase Model: Predictive model to predict which customer will repeat purchase in the last 12 months.
d.Match similar users, recommend the most popular content among those users.
e.Developed Lift Charts, ROC Curves, ggplots etc on various data sets.

2.Spam/Ham identification project:Real-time identifying and filtering of Spam vs Ham data from various multiple sources like Emails, Mobile SMS and Youtube Comments data using Kafka, Scala, Flink(4G of Bigdata), ElasticSearch, Cassandra and Machine Learning(FLinkML).

3.Proof of Concept on Image Processing, Audio Processing, Speech to Text and Video Processing using Python and Tensorflow for comparing and authentication and validity of the Source towards the target.

4. Created various Dashboards for POC on Watson Analytics like Churn Prediction, Customer Behaviour, HR Attrition, HR Discovery, Profit Dashboard, Tenure Discovery etc.

5.Telecom CDR Data Analysis: Real-time data processing and Big data storage to gain insight into operations by running query analysis against live feeds and event data. Extracted data from CSV files on real time basis using Spark and Streaming and moved into Cassandra NoSQL Database. Integrated Elastic Search and Presto for Search and Indexing facility and for faster querying, reporting and Visualize.
Reports: Volume_Timeout_CallRejected, IngressClientsQos etc..
6.Network optimization solution for a Tier1 Telecom for better customer service. Clients mobile routing server generates log files on real-time basis.

Work Terms

30 Hours/week