Post Job Free

Resume

Sign in

Data Engineer

Location:
Houston, TX
Posted:
June 29, 2020

Contact this candidate

Resume:

FENG (FRANK) FENG, Ph.D.

****B Petty St, Houston TX, 77007 979-***-**** add7il@r.postjobfree.com SUMMARY

A forward-thinking, self-motivated team player with 8 years of experience in modeling & programming Lawful permanent resident of U.S., available for full-time employment starting July-2020 EXPERIENCE

Independent Developer/Data Scientist, Houston, TX Dec 2019 - May 2020

Smart home system integration and proof of concept using opensource software and generic hardware: o Build a subscription-free, cloud-free home surveillance system using facial recognition, object detection, speech recognition and natural language processing (OpenCV/Facebox/SpeechRecognition/NLTK) o Real-time energy consumption optimization and demand response for appliances and HVAC using sensor data, real-time electricity price data, and peak-demand risk forecasts from ERCOT (A/B tests) Data Scientist/R&D Engineer, Kelvin Inc., The Woodlands, TX/San Francisco, CA Aug 2018 - Dec 2019

Developed/prototyped/deployed industrial IoT models (data-physics hybrid modeling, pattern recognition, operations research, Bayesian optimization, reinforcement learning, modeling with incomplete data): o Oil & gas production: anomaly detection, automation and optimization of various artificial lift types o Drilling & Completions: wellhead pressure anomaly detection, process optimization, torque & drag

Acted as the technical liaison for the customers and the interim technical product manager for Kelvin

Took the lead to combine domain knowledge and data science to provide novel solutions for production process monitoring, in sprint consulting projects, across multiple time zones (Databricks/PySpark/Azure) Reservoir Engineer/Data Scientist, University Lands, Houston, TX Sept 2017 - May 2018

Developed a well pad identification tool and dashboard for Spotfire with clustering methods (DBSCAN)

Built the first machine learning model for the team to predict oil & gas well production, using regression and boosting (Scikit-learn/Python), increased the accuracy by 30% than the existing physical model (RTA)

Initiated and coordinated the collaboration to use TAMU supercomputers for UL’s industrial applications

Build & calibrated multi-well reservoir simulation models for production forecast using high-performance computing (HPC) and optimization, which reveals the relationship between productivity and well spacing Graduate Research Assistant, Texas A&M University, College Station, TX Jan 2013 - Aug 2017

Proposed & built the first molecular rock physics model for flow simulation with HPC (Fortran/C++/GPU)

Used statistical analysis to determine permeability with the spatial & temporal simulation data (R/Python)

Analyzed the petroleum economics & production forecast using data from 2 million acres, comparing the impact of tax schedules in North Dakota, Montana, and Saskatchewan, published on Energy Strategy Reviews

Led a group of 5 to forecast commodity prices using time series data (LSTM/SARIMA/GARCH/Prophet) Graduate Research Assistant, Stanford University, Stanford, CA Aug 2011 - Jun 2012

Optimized the toxic metal removal for combustion process using reaction kinetics & transport simulation EDUCATION

M.S. in Statistics, Texas A&M University, College Station, TX/Remote GPA: 4.0 Jan 2017 - Aug 2020

Recommended the next vehicle to be purchased using car insurance data, review semantics, and market trend

Predicted COVID-19 propagation in rural Texas using spatial correlation, mobility, and demographics data Ph.D. in Petroleum Engineering, Texas A&M University, College Station, TX GPA: 3.8 Jan 2013 - Dec 2018 M.S. in Energy Resources Engineering, Stanford University, Stanford, CA GPA: 3.8 Aug 2011 - Jan 2013 B.S. in Chemistry & Physics, Peking University, Beijing, China GPA: 3.7 Sept 2006 - Jun 2011 TECHNICAL SKILLS

Data Science/Statistics/Machine Learning/Artificial Intelligence: Causal Inference, A/B test, R, SAS, SPSS, JMP, Scikit-learn, PyTorch, Keras, Tensorflow, AutoML (H2O), PyMC3, NLTK, OpenCV, Scikit-image

Business Analytics/Visualization: Spotfire, Tableau, Power BI, Qlik, Grafana, Kibana, Metabase, ArcGIS

Data Engineering/Cloud Computing: ETL, SQL, AWS, Azure, GCP, Spark, Hadoop, Databricks

Software Engineering/Programming: Python, Fortran, C/C++, Container (Docker, Kubernetes), CI/CD (Jenkins), Git, Unix Shell Scripting, Agile methodologies (JIRA), unit testing, parallel computing



Contact this candidate