|
The Junior Data Scientist works directly with the Senior Data Scientist to maintain accurate production, pressure, well-test and surveillance data, support daily and monthly reporting, and maintain the dashboards used by engineers and management. The role focuses on data quality control, maintaining and improving existing workflows, resolving issues, and understanding how field data is generated and why errors occur.
|
|
Performance Expectations:
- Data QC. Check daily and monthly production, pressure, well-test and ESP data from all assets for gaps, unit errors, sentinel values, duplicates and mis-allocated volumes. Trace problems back to the source and correct them.
- Workflows. Run, monitor and update the automated pipelines that load field data into SQL Server. Handle changes in source file formats, add new wells and facilities, and confirm that loads reconcile (rows in = rows loaded).
- Dashboards. Update and extend HTML and web dashboards and Excel reports as requirements change. Check charts visually as well as numerically before release.
- Bug fixes. Investigate bug reports from engineers, reproduce them, find the root cause, fix it and add a test where practical. Keep a short written record of each fix.
- Support. Answer data requests from reservoir, production and operations engineers, always citing the source table or file and the as-of date.
- Documentation. Keep scripts, data definitions and procedures documented so that someone else can run them.
- Work with production and surveillance data for all HKN assets, delivered through Excel workbooks, daily reports and SCADA/PI exports, and support internal web applications and HTML dashboards hosted on the company intranet.
- Use Python, SQL Server (pyodbc), FastAPI, Plotly, and Excel/Word/PowerPoint automation.
- Receive tasks from the Senior Data Scientist and seek clarification when a data question is unclear. Follow company security standards, including no credentials in code, parameterised SQL and authenticated access.
Competency (Knowledge & Skills) Required:
- Working Python, including pandas and numpy, and the ability to read and debug other people’s scripts.
- Working SQL, preferably SQL Server and T-SQL: joins, aggregations, and writing parameterised queries.
- Basic experience with a Python web framework, preferably FastAPI, or willingness to learn it quickly.
- Strong Excel skills, including reading complex workbooks and extracting data from them.
- Careful with numbers. You check totals, units and dates before you report a result.
Preferred knowledge and skills:
- Understanding of production operations: well tests, choke and rate data, water cut, ESPs, allocation, and bottom-hole pressure surveys.
- Familiarity with Git, plotting libraries such as Plotly, and the basics of IIS or Windows-hosted web applications.
- Exposure to time-series methods, such as decline curve analysis or basic forecasting.
Minimum Qualifications Required:
- Bachelor’s degree in petroleum engineering (preferred), or in another engineering, geoscience, computer science or statistics discipline.
- 0–3 years of experience in data analysis, data engineering or a technical role that works with production or reservoir data. Recent graduates with relevant project or internship experience are welcome.
- Good written and spoken English. Arabic or Kurdish is an advantage.
|
