Remote Europe: PDF Extraction Engineer

Convexio; United States; Remote; USD 66,000 - 99,000; Full time

Benefits offered by this job

Remote within Europe

Job summary

Convexio is seeking a role focused on improving extraction of structured information from complex PDFs that challenge standard OCR. The position blends document layout analysis, machine learning, practical heuristics, and rigorous evaluation to turn experimental improvements into dependable production systems.

You will work on challenging document formats, build benchmarks and evaluation methods, and analyze errors at the level of individual cells and tables.

Qualifications

• Interest in experimentation alongside responsibility for production-ready outcomes.
• Ability to investigate unusual data, visual artifacts, and persistent edge cases.
• A precise approach to quality, including failure patterns and reproducibility.
• Comfort evaluating extraction performance and tracing errors to their source.

Responsibilities

• Improve extraction pipelines for difficult document formats.
• Build and maintain benchmarks and evaluation methods for extraction quality.
• Investigate errors at fine detail, including individual cells and tables.
• Combine machine learning methods and classical heuristics to address document-specific challenges.
• Harden successful approaches for stable use in products and project work.

Skills

Experimentation

Quality mindset

Error tracing

Data investigation

Job description

Convexio is seeking a role focused on improving extraction of structured information from complex PDFs that challenge standard OCR. The position blends document layout analysis, machine learning, practical heuristics, and rigorous evaluation to turn experimental improvements into dependable production systems.

You will work on challenging document formats, build benchmarks and evaluation methods, and analyze errors at the level of individual cells and tables.