SUMMARY:

• Data Scientist with hands on experience in data analysis and track record creating actionable insight for complex high - tech products. Professional expertise include:
• Descriptive Analytics: establishing min data set of features and baselines.
• Exploratory Analytics: prototyping anomaly detection algorithm based on multiple subsets of features, performing dimensionality reduction.
• Data Preparation for raw data arriving in many different formats, Prototyping & Build-out of Analytical Models to be used in establishing most effective baseline for further computation.
• Certified in the state of art Data Science Approach and Tools via Galvanize: Statistics & Probability, Machine Learning Algorithms (Linear, Regularized and Logistic Regression, Non-Parametric Learners, Random Forest, SVM, Boosting), Clustering, Dimensionality Reduction, Recommendation Systems, NLP, NMF.

TECHNICAL SKILLS:

Programming languages: Python, R, Matlab, Octave, Java, SQL

Data Science Tools: scikit-learn, NumPy/SciPy/pandas, matplotlib, NLTK, bs4

Databases: PostgreSQL, SQLite, MySQL, MongoDB, Hive, Presto

Distributing Systems: Spark, Hadoop, MapReduce.

Version Control: Git, GitHub

PROFESSIONAL EXPERIENCE:

Confidential,San Francisco,CA

Data Scientist

Responsibilities:•

• Built K - means model designed to reduce over-authorization of readers assigned to employees, improve aviation workflow and reduce security threats by reclassifying access classes and their assignment to employees.
• Performed descriptive and exploratory analysis of network equipment data based on different data sources. Classified issues by related types and categories and used this classification for failure rate and mean time to failure prediction for purpose of raising overall service quality of equipment managed by Confidential .
• Analyzed SFO airport taxi traffic patterns and built model for managing taxi traffic congestion i.e. reducing taxis oversupply and freeing parking garage spaces.
• Applied NLP for reducing data redundancy and uncertainty in existing data bases as part of creating efficient data catalog that improved accuracy and enabled efficient functionality of data services.
• Designed and created externally facing web portal that accessed SFO noise data in real time and visualized noise data collectors by location in Tableau.

Confidential,San Francisco,CA

Data Scientist Consultant

Responsibilities:

• Built data quality checking and monitoring tools for off - line production processing pipeline that caught data integrity, correctness and accuracy issues as soon as possible.
• Performed metric quality analysis and drove investigation to fix issues that influenced quality of production workflows and ad-hoc analysis.

Confidential,East Palo Alto,CA

Data Scientist Consultant

Responsibilities:•

• Ported shell scripts that are managing AWS hadoop cluster into Python.
• Performed genomic data analysis on AWS hadoop cluster.

Confidential,San Francisco,CA

Data Scientist Fellow

Responsibilities:

• Intensive 12 weeks Data Science bootcamp covering the fundamentals of exploratory data analysis, machine learning, NLP and data visualization.
• Capstone Project: Human Activity Recognition Using Smartphones UCI Data Set - machine learning methods (Support Vector Machine, Random Forest, AdaBoost, XGBoost) applied on standing, sitting, laying, walking, walking upstairs and walking downstairs data set. Link: Activity Recognition

Confidential,Milpitas,CA

Senior Product Development Engineer

Responsibilities:

• Collected measurements on laser based silicon wafers scanning inspection system and performed detected defects data analysis using proprietary software that lead to customers issues resolution and new features development.
• Effectively worked with cross-functional teams in analyzing time sequential change in the number of defects and correlation between the number of defects and manufacturer process anomalies, resulting in cost reduction improvements.

Senior Applications Development Engineer

Responsibilities:

• Successfully developed method for optimizing optical aperture that improved rough film sensitivity and met customer requirements and deadlines, leading to multiple system orders.
• Performed data mining to determine similar defect signatures and their sources common technologies and processes, presented results and made recommendations to senior management that contributed to winning strategy and plan development.
• Participated in market research, developed product specifications, project plans, risk-benefit analysis, assigned resources to project tasks and led characterization involving US-India-China team coordination under time driven business critical situations.

Applications Development Engineer

Responsibilities:

• Participated in and led small and medium new feature characterization projects, and product demos.
• Responded to customer requests for improved defect detection with higher throughput, by performing problem diagnosis and developing problem resolutions.
• Received 2006 Business Unit award for Purchasing Order success for North America over $45M of bookings.

Data Modeling Engineer

Confidential,Silicon Valley, CA

• Developed simulation models of complex technical systems (GPS; spam detection; energy trading software), including requirements for the process modeling.
• Participated in defining product development processes.
• Integrated advanced optimization software in proprietary energy trading system.

Adjunct Lecturer / Teaching Assistant

Confidential,Santa Clara, CA

• Designed and taught labs and problem sessions for: Electromagnetics, Electric Circuits, Linear Systems, Modern Network Synthesis, Design and Fundamentals of Computer - Aided Circuit Simulations.
• Architected and developed software for simulation, optimization and control of large-scale electric power systems using optimization techniques and linear matrix inequality.

Associate Software Engineer

Confidential

• Analyzed, designed and developed the long-term hydro scheduling application using stochastic dynamic programming and method of successive approximations; performed client on-site installation and deployment of the software package; successfully met tight project deadlines.
• Designed functional specification and user’s manual, managed development of test procedures.
• Solely responsible for customization and maintenance of software for estimation of energy production cost. Led on site deployment and validation. Responsible for customer training.