Lead OCR/LLM Extraction Pipeline Engineer

Large-Scale Data Extraction Engineer – Subsurface & Well Documents
Urgent Requirement: Lead Data Pipeline Engineer – Large-Scale Document Extraction (OCR/LLM, 60k Documents)
We are seeking an experienced Data Engineer to configure and operate high-throughput AI document extraction pipelines for approximately 60,000 subsurface and well technical documents (~5 million pages) integrated into enterprise data stores.
Mandatory requirements:
1. High-Throughput Document Processing & Batch Orchestration
• Bachelor’s degree in Computer Science, Data Science, Geoscience, Petroleum Engineering, or related field.
• At least 5 years of data engineering experience, with at least 3 years focused on unstructured and semi-structured technical document processing.
• Proven, verifiable experience running large-volume document processing or digitization pipelines (tens of thousands of multi-page technical documents / millions of pages).
• Strong skills in batch orchestration, distributed processing, execution monitoring, rate-limiting, and error/exception handling under heavy workloads.
• Deep knowledge of document classification, layout analysis, OCR engines, and prompt engineering/GPT-based LLMs for structured metadata extraction from complex PDFs, tables, and scanned reports.
2. Data Quality, Enterprise Loading & Upstream Domain
• Advanced Python and SQL skills for large-scale data transformation, automated ETL/ELT pipelines, and data validation.
• Comprehensive understanding of document taxonomy, metadata standards, and end-to-end data lineage (page-level source attribution).
• Experience with PostgreSQL, Microsoft SQL Server, or enterprise search datastores.
• Experience preparing verified result packages for integration and loading into target enterprise repositories (reconciling loaded records and managing reject logs).
• Exposure to Upstream Oil & Gas subsurface and well data (well completion reports, G&G logs, seismic/core reports), industry standards (PPDM, OSDU), and Microsoft Azure (highly preferred).
• Professional English communication skills (mandatory); Portuguese fluency is a plus.
• Availability for an online technical interview in English.
• Availability to join the project if the contract is awarded.
Interested candidates should submit:
• Updated CV in English;
• Availability;
• Expected daily or monthly rate;
• Location and time zone;
• Detailed summary of past large-volume OCR/LLM document extraction projects (mention volumes, tools, and architecture).