About the job
Tiger Analytics is on the hunt for talented Data Scientists to join our rapidly expanding advanced analytics consulting firm. Our team is comprised of experts in Data Science, Machine Learning, and Artificial Intelligence. As a trusted analytics partner for numerous Fortune 500 companies, we empower these organizations to derive significant business value from their data. Our exceptional performance and leadership have been acknowledged by leading market research institutions, including Forrester and Gartner. We are committed to building the world's finest global analytics consulting team and are seeking extraordinary talent to join us.
We are currently in search of a Data Scientist with substantial downstream refining experience to facilitate data-driven insights across refinery operations, economics, and reliability. This role involves collaborating closely with process engineers, operations, planning, maintenance, and commercial teams to enhance refinery performance through advanced analytics and machine learning techniques.
In this position, you'll tackle high-impact challenges such as optimizing yield, improving energy efficiency, enhancing unit reliability, conducting predictive maintenance, and boosting margins, transforming intricate refinery data into actionable intelligence.
Analytics & Modeling
- Design, validate, and implement statistical, machine learning, and optimization models tailored for refining operations
- Develop models for:
- Optimizing unit performance (e.g., CDU/VDU, hydrotreating, cracking)
- Enhancing energy efficiency and utilities management
- Yield and cut-point optimization
- Predictive maintenance and reliability analytics
- Detecting fouling, corrosion, and anomalies
- Utilize time-series analysis on high-frequency plant data (DCS, historian)
Refining Domain Collaboration
- Collaborate with process engineers, operations, maintenance, and planning teams to translate refinery challenges into analytical solutions
- Integrate first-principles knowledge (mass & energy balances, constraints, process limits) into data models
- Interpret model outcomes concerning refinery economics, safety, and operability
Communication & Impact
- Effectively convey insights to both technical and non-technical stakeholders
- Measure business impact including margin enhancement, energy savings, and reliability improvements
