Software Engineer Resume Milpitas CA - Hire IT People

SUMMARY

Spark/PySpark, Scala, Hadoop, MapReduce
SQL/MySQL, NoSQL, Hive, Pig, Phoenix
Scikit - learn, SparkML/MLlib, Turi ML Tools, TensorFlow, R, Keras, MXNet
XGBoost, Random Forest, AI, Deep Learning, Reinforcement Learning, SVM, Logistic Regression, Clustering, PCA, NLP, Topic Modeling, Recommendation Systems
HUE, Qubole, Jupyter, ETL, Oozie, GitHub
Python, JAVA, C/C++, Linux Scripting
AWS, Amazon S3

PROFESSIONAL EXPERIENCE

Software Engineer

Confidential . Milpitas CA

Responsibilities:

Develop Anomaly Detection Engine using Spark/Scala
Recommendation Engine / Pattern Mining for customer needs
Predictive models using Ensemble Modeling for customer behavior predictions
Causal Analysis using Deep Learning(TensorFlow)
Segmentation on customer using Topic Modeling/Text Mining
Responsible for building new and additional features in the core product. Building a Journey Engine based on NLP, Text Cleaning, Text Mining and Aggregations.
Predictive models using XGBoost, Deep Learning (CNN/Word2vec), Regularization and Ensemble Modeling for customer behavior predictions
Recommendation Engine / Frequent Pattern Mining for customer needs
Forecasting and Segmentation problems using LDA and Text Clustering DBSCAN(T-SNE)

Data Analyst

Confidential San Francisco CA

Responsibilities:

Analyzing large-scale data using Sequential Pattern Mining, Text Clustering, Topic Modeling and Predictive Modeling wif PySpark/Python
Generate Pipeline using PySpark, SparkSQL and Hive
ETL Scheduling and Deployment data using Python, Hive and Oozie
Using Google Analytics and SQL to analyze data
Implementing API using Python
Using Hive/SQL to extract, transform and store data and generate business metrics; Conducting feature engineering and data Preprocessing
Analyzing complex data sets, predictive modeling, machine learning, and/or large-scale data mining using PySpark/Python
Using ML tools (Scikit-Learn) and statistical models such as Classification, Gradient Boosted Decision Tree, Random Forest, Ensemble Methods, Logistic Regression, Cluster analysis, PCA and Semi-Supervised Learning methods to solve real data problems
Conducting text analysis, Recommender Systems and script programming to analyze interesting problems

Data Analyst

Confidential

Responsibilities:

Data manipulation and Data management wif R programming, descriptive analysis
Using various statistical models such as classification Decision Tree, Bayesian Analysis, Naive Bayes Spam Filtering, Logistic Regression, Cluster analysis, PCA, Neural Network, SVM, EM methods and script programming to analyze user behavior
Involving in reporting statistical findings to work colleagues and senior managers
Using statistical programming wif SAS MACRO, SAS programming; SPSS,MS Access to analyze data
Using experimental design analysis, repeated measure analysis and hypothesis testing to study product performance
Conducting statistical analysis and survey of marketing, descriptive analysis, categorical data analysis, power analysis, nonparametric analysis