About the Team

We are part of the Legal & Automation Tools Chapter, responsible for building solutions that connect key endpoints and enable users to generate all required documents for our correspondence services across multiple markets.

We are in the middle of a major technical transformation, making this the perfect time to join and influence the future of our systems. Our current focus is on intelligent document processing, language model development, and multilingual text automation to support legal and collections-related processes.

While we still maintain some existing workflows, the majority of our work is innovation-driven, focusing on new features, advanced text understanding, and automation of complex document flows.

We work in close collaboration with Product Owners, Business Analysts, and Testers, with a strong emphasis on knowledge sharing, engagement, and collaborative problem solving. Work is fully remote with occasional visits to the Wrocław office.

Key Responsibilities

Design and implement Intelligent Document Processing (IDP) solutions for legal, notification, and collections-related documents
Develop and fine-tune Natural Language Processing (NLP) and language models to handle multilingual content across different markets
Integrate OCR/AI tools (e.g., Azure Document Intelligence, Azure Computer Vision, Tesseract) to extract structured and unstructured data from diverse document formats
Build pipelines for document classification, data extraction, and entity recognition with high accuracy rates
Collaborate with business teams to understand document lifecycles and identify automation opportunities
Work with confidence scoring, human-in-the-loop review processes, and feedback loops to improve extraction models
Develop and maintain APIs, data transformation scripts, and automation components supporting document workflows
Monitor, evaluate, and continuously optimize accuracy, performance, and scalability of NLP and IDP models
Share expertise and best practices within the automation and AI team

Qualifications

Must-Have:

2+ years of experience in IDP or NLP development
Practical experience with OCR/IDP tools (Microsoft Azure Document Intelligence, Azure Computer Vision, Tesseract, ABBYY, or equivalent)
Strong understanding of NLP techniques, text parsing, tokenization, lemmatization, entity recognition, and language detection
Experience building and tuning language models for multilingual contexts
Proficiency in Python for data processing and model integration (e.g., using libraries like spaCy, NLTK, Hugging Face Transformers)
Experience with REST APIs, JSON, and data transformation workflows
Good command of English (minimum B2/C1) for international collaboration
Experience with Azure cloud services

Nice to Have:

Familiarity with machine learning frameworks (e.g., TensorFlow, PyTorch)
Experience with RPA platforms (UiPath, Power Automate) as part of document workflow orchestration
Understanding of workflow orchestration, document classification, or confidence scoring
Awareness of IT security and compliance requirements in document processing

What We Offer

Employment contract or B2B cooperation - your choice
Flexible working hours (start between 6:00-11:00)
Fully remote work or hybrid model (occasional Wrocław office visits)
Employee benefits: private medical care (Luxmed), Multisport card subsidy, cafeteria system, group insurance
Attractive employee referral program bonus
Option to rent a company car for private use