We provide IT Staff Augmentation Services!

Sr. Consultant For Big Data/data Science Resume

UsA

SUMMARY:

  • Strong expertise in leveraging the cutting - edge technology to address business/behavior intelligence, data governance, security, compliances, disaster recovery, backup/migration, testing & release management.
  • Hands on experience with Hadoop HDFS, HBase, MongoDB, HiveQL, NLTK text mining, sklearn, numpy, matplotlib, Tensor flow, Keras and few NN’s pandas, EDW, Kafka, AWS EC2, dynamo, S3 RDS, & Azure cloud, blob containers, DW using data structures, applying OOPS and own and canned algorithms
  • Strong domain knowledge in Financial, E-Commerce, Social, Manufacturing & Healthcare
  • Lead the DevOps and BI teams with DaaS and PaaS along with Docker implementation, tokenize based API Microservices with dual factor authentication & Virtual Private Security.
  • Consolidated 2 Silicon Valley datacenter creating a saving of 3 quarters of million.

PROFESSIONAL EXPERIENCE:

Confidential

Sr. Consultant for Big data/Data Science

Responsibilities:

  • Architected the migration process of the existing SAP BIDW to Azure Sql server & Hadoop clusters. Heavy involvement Hive were used.
  • Designed, developed the Machine Learning process for the data science & visualization team with deep text mining for Da-Vinci Robotic systems using Azure Cloud
  • Created customized medical keywords search engine using Python NLTK, Stanford NER, word net corpus. This helped 80% search improvement for phone support customers
  • Identification and removal of PHI data (eliminated 95%+ lawsuit), encryption of PII data from HIPAA cloud using Stanford NER and NLTK based NER, and stored into Azure blob container.
  • Brought marketing campaign data using API from survey monkey, Qualtrics and created sentiment score, Net Promoter score
  • Created 5 cluster buckets for reported procedure various surgery information that are given to Food and Drug Administration using Support Vector machines (SVM) algorithms.
  • Various trial and error of using KNN, Naïve Bayesian, Random Forest, linear, logistic regression algorithms to solve business problems
  • Created bench mark between MongoDB vs Mark Logic NoSQL on performance, adaptability, scalability, security and many more.
  • POC is currently undergoing for an Insurance company to minimize the scrap loss when totaling the vehicles. Currently used Tensor flow, Keras, Convolutional Neural Network (AI) to identify the percent of damage of a car based on the images submitted by Insurance appraiser. Then this information is used along with various factors from the vehicle (year, make, model, owner and many others) and come up with a decision making to total the car or not along with a rate to the insurance adjuster. The adjuster has his own discretion.

Hire Now