
Senior Python Developer, Document Processing Specialist
Sciensa
contract
Posted on:
Location Type: Remote
Location: Brazil
Visit company websiteExplore more
Job Level
About the role
- Develop and maintain Python solutions for intelligent document processing;
- Structure and normalize data extracted from unstructured documents (PDFs, images, scans, etc.);
- Implement and optimize regex rules for identifying and validating textual patterns;
- Work with OCR tools (e.g., Tesseract, AWS Textract, Azure Form Recognizer, Google Vision, or similar);
- Build extraction, transformation, and data validation pipelines;
- Analyze complex documents (contracts, forms, invoices, statements, and others);
- Ensure the quality, accuracy, and scalability of solutions.
Requirements
- Strong experience with Python (senior or specialist level);
- Proven experience in:
- Structuring data from documents;
- Advanced regular expressions (regex);
- OCR and image/text processing;
- PDF handling (e.g., pdfplumber, PyMuPDF, PDFMiner, OpenCV);
- Working with unstructured data;
- Strong analytical skills and attention to detail.
- Differentials / Nice-to-haves:
- Experience with NLP (spaCy, transformers, LLMs);
- Knowledge of machine learning applied to documents;
- Experience with data pipelines and automation;
- Experience handling large volumes of documents;
- Experience in Document AI projects.
Benefits
- Equipment: Provided by Sciensa, according to the needs of the area/project.
- Paid allowance: 15 days after 12 months of contract (to recharge your energy!).
Applicant Tracking System Keywords
Tip: use these terms in your resume and cover letter to boost ATS matches.
Hard Skills & Tools
Pythonregular expressionsOCRimage processingPDF handlingdata pipelinesNLPmachine learningdata validationdocument processing
Soft Skills
analytical skillsattention to detail