Data Scientist (Oil and Gas)
Share
Job Location:
Houston, MS - USA
Monthly Salary:
Not Disclosed
Posted on:
4 days ago
Vacancies:
1 Vacancy
Job Summary
No sponsorship is available now or in the future. 3 days onsite in HoustonTX (Downtown)
Title:Data Scientist (Oil and Gas)
Location: HoustonTX - Hybrid 3 days in office
Type of Role: Full time
Title:Data Scientist (Oil and Gas)
Location: HoustonTX - Hybrid 3 days in office
Type of Role: Full time
Description
We are seeking a Data Scientist with strong downstream refining experience to drive data-
driven insights across refinery operations economics and reliability. This role partners
closely with process engineers operations planning maintenance and commercial teams
to optimize refinery performance using advanced analytics machine learning and domain-
informed modeling.
Youll work on high-impact problems such as yield optimization energy efficiency unit
reliability predictive maintenance and margin improvement-turning complex refinery data
into actionable intelligence.
We are seeking a Data Scientist with strong downstream refining experience to drive data-
driven insights across refinery operations economics and reliability. This role partners
closely with process engineers operations planning maintenance and commercial teams
to optimize refinery performance using advanced analytics machine learning and domain-
informed modeling.
Youll work on high-impact problems such as yield optimization energy efficiency unit
reliability predictive maintenance and margin improvement-turning complex refinery data
into actionable intelligence.
Analytics & Modeling
Develop validate and deploy statistical ML and optimization models for refining
operations
Build models supporting:
o Unit performance optimization (e.g. CDU/VDU hydrotreating cracking)
o Energy efficiency and utilities optimization
o Yield and cut-point optimization
o Predictive maintenance and reliability analytics
o Fouling corrosion and anomaly detection
o Apply time-series analysis to high-frequency plant data (DCS historian)
Develop validate and deploy statistical ML and optimization models for refining
operations
Build models supporting:
o Unit performance optimization (e.g. CDU/VDU hydrotreating cracking)
o Energy efficiency and utilities optimization
o Yield and cut-point optimization
o Predictive maintenance and reliability analytics
o Fouling corrosion and anomaly detection
o Apply time-series analysis to high-frequency plant data (DCS historian)
Refining Domain Collaboration
Partner with process engineers operations maintenance and planning
teams to translate refinery problems into analytical solutions
Incorporate first-principles knowledge (mass & energy balances constraints
process limits) into data models
Interpret model results in the context of refinery economics safety and operability
Communication &; Impact
Clearly communicate insights to technical and non-technical stakeholders
Quantify business impact (margin improvement energy reduction reliability gain
Partner with process engineers operations maintenance and planning
teams to translate refinery problems into analytical solutions
Incorporate first-principles knowledge (mass & energy balances constraints
process limits) into data models
Interpret model results in the context of refinery economics safety and operability
Communication &; Impact
Clearly communicate insights to technical and non-technical stakeholders
Quantify business impact (margin improvement energy reduction reliability gain
Responsibility
Bachelors or Masters degree in Data Science Chemical Engineering Applied
Mathematics Statistics or related field
Bachelors or Masters degree in Data Science Chemical Engineering Applied
Mathematics Statistics or related field
3 8 years of experience applying data science in downstream refining or closely
related process industries
Strong proficiency in Python or R for data analysis and modeling
Experience with time-series data and industrial process data
Solid understanding of refining processes and unit operations
Experience working with historians (PI) SQL databases and unstructured data
related process industries
Strong proficiency in Python or R for data analysis and modeling
Experience with time-series data and industrial process data
Solid understanding of refining processes and unit operations
Experience working with historians (PI) SQL databases and unstructured data
