Profession & Experience

‍I am a Data Scientist and Petroleum Engineer with 6+ years across upstream/downstream energy and data disciplines - spanning production engineering, subsurface modelling, end-to-end data curation, and agile product ownership. Experience includes Viridien (Data Scientist), TechPet Global (Petro-Technical Analyst), OGDCL (Production Engineer), and academic facilitation at Imperial College London.

Data Scientist at Viridien (Aug 2022–present) in Llandudno, Wales. Acts as Product Owner for agile data-curation initiatives focused on large-scale ingestion, deduplication, classification, and dashboarding—facilitating stand-ups, reviews, and retrospectives to improve coordination and delivery speed while translating business needs into analytical solutions.

Combines deep petroleum domain knowledge with modern data science and data-engineering practices to turn messy, unstructured subsurface information into reliable, analysis-ready assets. Known for end-to-end ownership (from ingestion and QC to modelling and visualization), pragmatic stakeholder communication, and shipping tangible improvements to data quality and decision velocity.

‍

Main areas of expertise:

• Data engineering & curation: Built end-to-end ETL pipelines integrating Python, Neo4j, Power Query, and PostgreSQL to deliver high-quality, production-grade data into client databases.
• Machine learning & unstructured data: Applied ML for subsurface data clustering/classification and implemented document parsing workflows; co-developed an automated QC tool for PVT data with robust sample ranking logic.
• Subsurface/petroleum engineering: Field data analysis, reservoir modelling, integrated production system simulation, history matching, and production optimization.
• Analytics & visualization: Dashboard design (Power BI) and trend discovery to inform decisions across technical and non-technical stakeholders.
• Ways of working: Agile/Scrum ceremonies, backlog prioritization, sprint planning, and stakeholder alignment; Scrum Master Certified (SMC).
• ‍

Current situation:

Data Scientist at Viridien (Aug 2022–present) in Llandudno, Wales. Acts as Product Owner for agile data-curation initiatives focused on large-scale ingestion, deduplication, classification, and dashboarding—facilitating stand-ups, reviews, and retrospectives to improve coordination and delivery speed while translating business needs into analytical solutions.

‍

Value proposition & differentiators:

Combines deep petroleum domain knowledge with modern data science and data-engineering practices to turn messy, unstructured subsurface information into reliable, analysis-ready assets. Known for end-to-end ownership (from ingestion and QC to modelling and visualization), pragmatic stakeholder communication, and shipping tangible improvements to data quality and decision velocity. Highlights include:

• Delivered production ETL pipelines (Python/Neo4j/Power Query/PostgreSQL) for client-grade data curation.
• Implemented ML-driven clustering/classification and document parsing for subsurface datasets.
• Co-developed an automated PVT data QC and ranking approach adopted in delivery workflows.
• ‍

Extras:

• Tools: Python, Neo4j, Power Query, PostgreSQL, Power BI.

• Certifications: Scrum Master Certified (SMC); Graph Analytics for Big Data; Data Science Methodology; Tools for Data Science.

• Languages: English (Full Professional); Urdu (Full Professional); Pashto (Native/Bilingual); Hindi (Limited).

• Publications:
  • Leveraging Advanced Technologies to Curate and Visualize Unstructured Geochemistry and PVT Documents
  • End to End Data Curation and Transformation with a Unique Data Quality Workflow: PVT case study

Data Scientist, Viridien — Llandudno, Wales, Aug 2022–Present

Product Owner and data scientist driving two agile data-curation initiatives across large-scale ingestion, de-duplication, classification, and dashboard visualization. I lead backlog prioritization and sprint planning to align work to business outcomes, and facilitate daily stand-ups, reviews, and retrospectives to improve coordination and delivery time.

Built and maintained end-to-end ETL pipelines integrating Python, Neo4j, Power Query, and PostgreSQL to deliver production-grade, high-quality data into client environments. Applied petroleum engineering expertise to QC extracted data, identify trends, and shape decision-ready dashboards for technical and non-technical stakeholders.

• Key achievements: Implemented ML-based clustering/classification and document-parsing workflows for subsurface datasets; co-developed an automated QC approach for PVT data with robust sample-ranking logic; consistently translated business needs into analytical solutions that enhanced service value.