AI Engineer / Data Engineer (m/f/d) - Document Intelligence & SAP Integration - German Required
⚲ Warszawa
Do uzgodnienia
Wymagania
- Python
Opis stanowiska
More about us
Billennium is a global technology company with over 20 years of experience, committed to innovation and empowering businesses. As an employer, we offer a supportive, growth-focused environment where collaboration and creativity thrive. Join us to shape the future of technology together!
About the role
We're looking for an experienced AI Engineer / Data Engineer (m/f/d) and good German skills to join our team.
Key Responsibilities:
• Source Document Analysis: Analysis of document and image repositories regarding document types, information content, data quality, layout variations, nameplate variants, handwritten content, table structures, and technical drawings.
• Extraction Solution Design: Development of a target architecture for OCR processing, Document Intelligence, Vision AI, Large Language Models, Data validation rules, Quality assurance processes.
• AI Component Development: Development and configuration of AI components for image and document analysis.
• Data Structuring: Transformation of extracted information into Business-defined target objects, SAP-compliant data structures, CSV/JSON formats, SAP import formats.
• Quality Assurance: Implementation of Completeness checks, Plausibility checks, Confidence scoring, Error classification.
• Pilot Implementation: Execution of a pilot based on a defined document repository, including Validation of extraction quality, Measurement of recognition rates, Identification of optimization opportunities.
• Documentation: Creation of Technical and operational documentation, Architecture overview, Data model description, Handover documentation.
Requirements:
· Computer Vision & Document AI: OCR, Vision LLMs, image classification, object detection.
· Generative AI: Large Language Models, Prompt Engineering, Information Extraction, Structured Output Generation.
· Document Processing: PDF analysis, scan processing, table extraction, layout analysis, handwriting recognition.
· Data Engineering: Python, Pandas, Databricks.
· Strong English skills, ideally C1.
· Strong German skills, at least B2.
· Nice-to-have Skills: MLOps, GDPR-compliant AI solutions, Microsoft Document Intelligence, Azure AI Vision, OpenCV, PySpark, Delta Lake, SAP attribute models.
Perks and benefits:
•
Comprehensive benefits - enjoy Udemy for Business, private medical care, Multisport card, veterinary package, language lessons, and shopping vouchers.
• Flexibility - adaptable working hours and remote/hybrid work options to suit your lifestyle & location.
• Career growth - access opportunities for professional development and learning, including perks related to our official partnerships with global IT giants: Microsoft, AWS, Snowflake, Salesforce & more.
• Global collaboration - work with a diverse, international team.
• Innovative environment - be part of a forward-thinking and growth-oriented workplace.
• Engaging community – Work with passionate professionals and participate in team-building events, hackathons, and CSR initiatives to make an impact beyond work.
• Team-building events including our company tradition (annual company event in Mazury).
• A pleasant surprise to start your journey with us in the form of a welcome pack.
Recruitment process:
• HR call
• Technical Interview
• Interview with the dedicated Client
• Final decision/ Feedback
Sounds interesting? Click "Apply" and have a chance to hear more!
Billennium is a global technology company with over 20 years of experience, committed to innovation and empowering businesses. As an employer, we offer a supportive, growth-focused environment where collaboration and creativity thrive. Join us to shape the future of technology together!
About the role
We're looking for an experienced AI Engineer / Data Engineer (m/f/d) and good German skills to join our team.
Key Responsibilities:
• Source Document Analysis: Analysis of document and image repositories regarding document types, information content, data quality, layout variations, nameplate variants, handwritten content, table structures, and technical drawings.
• Extraction Solution Design: Development of a target architecture for OCR processing, Document Intelligence, Vision AI, Large Language Models, Data validation rules, Quality assurance processes.
• AI Component Development: Development and configuration of AI components for image and document analysis.
• Data Structuring: Transformation of extracted information into Business-defined target objects, SAP-compliant data structures, CSV/JSON formats, SAP import formats.
• Quality Assurance: Implementation of Completeness checks, Plausibility checks, Confidence scoring, Error classification.
• Pilot Implementation: Execution of a pilot based on a defined document repository, including Validation of extraction quality, Measurement of recognition rates, Identification of optimization opportunities.
• Documentation: Creation of Technical and operational documentation, Architecture overview, Data model description, Handover documentation.
Requirements:
· Computer Vision & Document AI: OCR, Vision LLMs, image classification, object detection.
· Generative AI: Large Language Models, Prompt Engineering, Information Extraction, Structured Output Generation.
· Document Processing: PDF analysis, scan processing, table extraction, layout analysis, handwriting recognition.
· Data Engineering: Python, Pandas, Databricks.
· Strong English skills, ideally C1.
· Strong German skills, at least B2.
· Nice-to-have Skills: MLOps, GDPR-compliant AI solutions, Microsoft Document Intelligence, Azure AI Vision, OpenCV, PySpark, Delta Lake, SAP attribute models.
Perks and benefits:
•
Comprehensive benefits - enjoy Udemy for Business, private medical care, Multisport card, veterinary package, language lessons, and shopping vouchers.
• Flexibility - adaptable working hours and remote/hybrid work options to suit your lifestyle & location.
• Career growth - access opportunities for professional development and learning, including perks related to our official partnerships with global IT giants: Microsoft, AWS, Snowflake, Salesforce & more.
• Global collaboration - work with a diverse, international team.
• Innovative environment - be part of a forward-thinking and growth-oriented workplace.
• Engaging community – Work with passionate professionals and participate in team-building events, hackathons, and CSR initiatives to make an impact beyond work.
• Team-building events including our company tradition (annual company event in Mazury).
• A pleasant surprise to start your journey with us in the form of a welcome pack.
Recruitment process:
• HR call
• Technical Interview
• Interview with the dedicated Client
• Final decision/ Feedback
Sounds interesting? Click "Apply" and have a chance to hear more!
🔍 Dekoder Ogłoszenia
🟡
supportive, growth-focused environment where collaboration and creativity thrive
Może oznaczać, że firma stawia na rozwój pracowników i dobrą atmosferę, ale równie dobrze może być standardowym frazesem bez konkretnych działań.
🟡
experienced AI Engineer / Data Engineer
Chociaż brzmi to jak poszukiwanie eksperta, może oznaczać, że firma szuka osoby z pewnym doświadczeniem, ale niekoniecznie na poziomie seniorskim.
🔴
Development of a target architecture for OCR processing, Document Intelligence, Vision AI, Large Language Models, Data validation rules, Quality assurance processes.
Szeroki zakres odpowiedzialności, który może oznaczać, że będziesz musiał zajmować się wieloma różnymi technologiami i procesami, a nie tylko wąską specjalizacją.
🔴
SAP-compliant data structures, CSV/JSON formats, SAP import formats
Wskazuje na konieczność pracy z systemem SAP i jego specyficznymi formatami danych, co może być wyzwaniem, jeśli nie masz z nim doświadczenia.
🟡
Execution of a pilot based on a defined document repository, including Validation of extraction quality, Measurement of recognition rates, Identification of optimization opportunities.
Oznacza, że będziesz odpowiedzialny za wdrożenie i ocenę nowego rozwiązania, co może być zarówno szansą na wykazanie się, jak i dodatkowym obciążeniem.