Big Data Consultant Resume
SUMMARY:
- 4+ years in Big Data & Data science with hands on Data processing, cleansing and verifying the integrity of data used for Machine learning.
- 2+ years in the Machine learning / NLP application development with Hadoop, Pig, Hive, Spark & R.
- 2+ Years in the Hive Data modeling and Hive advance Analytics.
- 2+ years in the Data ingestion and ETL experience.
- Accomplished Senior Data Scientist with 5+ years of hands - on experience in Hadoop technologies, Data analysis, Data engineering and Data modeling in Hadoop and 4+ years of experience in Research and academic experience.
- Strong hands-on Engineering experience in Data ingestion, data storage, data analysis, data modeling and building features and optimizing classifiers using machine learning techniques.
- Strong hands on experience in Hive, SPARK (SPARK SQL), Python, R, Pig, Sqoop, Flume, Oozie and Hive. Substantial hands-on experience in Tableau, PowerBI, IBM Watson Analytics, plot.
TECHNICAL SKILLS:
Hadoop expertise: Hortonworks 2.x Pig, Hive (LLAP, TEZ), Sqoop, SPARK, Flume, Ranger, Knox, Kerberos, HDFS, YARN, Oozie, Ambari, Atlas, Kafka; Cloudera5.X Hive, Pig, HDFS, Flume, Spark, Sqoop, Kafka, HBase
Data Science expertise: Data Science with Python and R, Machine learning and Deep Learning
Machine Learning expertise Regression: linear, multiple linear, polynomial, support vector, decision tree, random forest; Classification logistic regression, K-Nearest neighbors (K-NN), support vector machine (SVM), kernel SVM, Naive Bayes, decision tree, random forest; Clustering K-means, hierarchical; Dimensional reduction Principal Component Analysis (PCA), kernel PCA; Deep Learning Artificial Neural Networks, Convolutional Neural Networks;
Other technical capabilities: Python 2.x/3.x (NumPy, SciPy, Pandas, Sickie Learn, Matplotlib, Spark), Shell Scripting, JSON/XML, Oracle/MySQL/PostgreSQL, Windows, Ubuntu, Active Directory (AD), LDAP, DWH, Anaconda and Eclipse, Tableau
PROFESSIONAL EXPERIENCE:
Confidential
Big Data Consultant
Responsibilities:
- Designed and Developed a data ingestion framework to acquire data from social media such as twitter logs, marketing channels, Teradata- EDW source and third-party demographic database using Hadoop, Sqoop, Spark streaming, MiFi, and Oozie
- Built a customer sentiment analysis through natural language processing by employing machine learning algorithms such as PCA (principle component analysis), k-means clustering, and logistic regression on the collected data set using Python and Hive
- Performed data modeling, data enrichment and data analysis using Hive and Spark programming
- Created dashboard visualization using Tableau
Environment: Hortonworks, Hadoop, Spark, Spark streaming, Sqoop, NiFi,Kafka, Oozie, Ambari, Python, Shell script
Confidential
Senior Big Data Dev /Data Scientist
Responsibilities:
- Performed Spark processing, Spark ML using TensorFlow to classify the Images
- Created Hive Data Modeling and stores the Result into Data lake
- Ingest IoT event data across geographical to data lake
- Ingest CSV file using Flume, Oracle RDBMS data using Sqoop
- Using Pig performed ETL for incoming data
- Designed and created an Artificial Intelligence based mobile App for classification of water samples based on bacterial contamination
- Built Tableau dashboards for water quality data analytics
- Developed a model to predict the E. coli (bacteria) outbreaks
Environment: Hortonworks, Hadoop, HDFS, YARN, Spark, Spark SQL, Spark ML, Pig, Hive, Google’s TensorFlow, Android Studio, Sqoop, SOSCIP cloud, Tableau, IBM Watson Analytics
Confidential
Lead Product Developer
Responsibilities:
- Acquired the microscopic images of the malaria infected blood cell and ingested the images into data lake
- Performed data transformation using Pig and data analysis using Hive
- Developed a machine learning algorithm based on probabilistic k-mean clustering (PkMC) for automated and unsupervised detection of malaria infected blood cells from the images of blood samples
- Classified the images based on number of malaria infected blood cells.
- Built online web-based portal as well as android mobile App for uploading the images into data lake
Environment: Python, MATLAB Image Processing, ImageJ, probabilistic k-mean clustering algorithm, Pig Hive, Android Studio
Confidential
Founder, innovator, Lead Product Developer
Responsibilities:
- Founded Startup based on original concept that does not exist in Market Place
- Developed Internet of Things (IoT) based rapid diagnostic device, Cardio Chip, for early detection of heart attacks from the blood sample of patients
- Designed innovative new User Interface to the IoT based Cardio Chip
- Performed laboratory and clinical trials on Cardio Chip and collected the data of biomarker levels
- Data is cleaned, drawn insights, and predicted the heart attack prone patients/blood samples
Environment: Python, Django, IoT, MATLAB, SQL, Microsoft Excel and Word
Confidential
Graduate Research Assistant/Postdoctoral Fellow
Responsibilities:
- Acquired the series of images of a sessile drop spreading on the surface as well as the pendant drop kept in air/viscous media
- Data is ingested into ImageJ and processed the images using Python scripts for wetting properties such as contact angle and surface tension
- Compared the experimentally determined contact angles and surface tension values using theoretical models
Environment: Python, ImageJ, Origin Lab, Microsoft Excel and Word, Latex
