AI Developer

Summary

Andersen is looking for an AI Developer for a project with a global energy company. The role involves creating AI solutions for document processing to support digital transformation and improve efficiency.

The customer is a global leader in energy technology, operating in over 90 countries with approximately 100,000 employees. With a comprehensive portfolio that spans conventional power generation, grid infrastructure, and renewable energy, the organization plays a vital role in enabling the global energy transition. The customer is committed to decarbonizing the energy sector, investing over €1 billion annually in research and development to drive sustainable, reliable, and affordable energy solutions.

The project is part of a major digital transformation initiative focused on AI and automation to modernize infrastructure and enhance operational efficiency. It aims to develop a document ingestion and content extraction solution using advanced AI technologies. As part of this effort, the team will design and implement core components to streamline document processing and support smarter, data-driven decision-making across the organization.

Responsibilities

• Developing robust pipelines to process PDFs, including scanned documents and text-heavy files.
• Applying OCR techniques (e.g., Tesseract, AWS Textract) and LLM-based methods for extracting structured and unstructured data.
• Integrating tools like Unstructured.io, MinerU, and Pydantic for parsing, validation, and modeling.
• Designing and implementing LLM-enhanced workflows, including prompt engineering, RAG pipelines, and retrieval-enhanced applications.
• Exploring frameworks such as LangChain, LlamaIndex, or custom orchestration layers for intelligent document comprehension.
• Building and deploying services using Docker, AWS ECS, and Lambda, following event-driven architecture principles.
• Ensuring secure and efficient integration of third-party AI/ML services.
• Participating in daily stand-ups, biweekly syncs, and technical interviews.
• Collaborating with distributed teams across Germany, India, and the U.S.
• Contributing to strategic discussions around expanding the solution into broader AI/LLM initiatives, including agent development and model fine-tuning.

Requirements

• Hands-on Python development experience, with a strong focus on building robust, scalable systems for 5+ years.
• Extensive experience processing large volumes of documents, including unstructured and semi-structured formats (PDFs, scanned documents, text-heavy files).
• Proven ability to extract content from documents, especially PDF files containing a mix of text and scanned imagery, using both rule-based and ML/LLM-based techniques.
• Practical experience leveraging LLMs for content extraction, including prompt engineering, RAG pipelines, or integrating LLMs into document processing workflows.
• Hands-on knowledge of document intelligence services, such as AWS Textract and/or Azure Document Intelligence, for OCR and structured data extraction.
• Proficiency in deploying applications using containers (Docker) and orchestrating services with AWS ECS and Lambda, with a good understanding of event-driven architectures.
• Familiarity with key tools and libraries for content extraction, including Tesseract OCR, Unstructured.io, MinerU, Pydantic.
• Strong understanding of data pipelines and modular service design with Python.
• Ability to work with cloud-native workflows and integrate third-party ML/AI services securely and efficiently.
• Clear written and verbal communication skills.
• Level of English – from Upper-Intermediate and above.

Desired skills

• Experience building RAG pipelines or retrieval-enhanced LLM applications.
• Exposure to GenAI frameworks such as LangChain, LlamaIndex, or custom-built LLM orchestration layers.
• Background in pre-processing and chunking strategies to enhance document comprehension by AI models.
• Prior experience in a GenAI-focused project environment, especially in a consulting, startup, or agile enterprise setting.

Reasons to join us

• Experience in teamwork with leaders in FinTech, Healthcare, Retail, Telecom, and others. Andersen cooperates with such businesses as Samsung, Siemens, Johnson & Johnson, BNP Paribas, Ryanair, Mercedes, TUI, Verivox, Allianz, T-Systems, etc..
• The opportunity to change the project and/or develop expertise in an interesting business domain.
• Job conditions – you can work both fully remotely and from the office or can choose a hybrid variant.
• Guarantee of professional, financial, and career growth! The company has introduced systems of mentoring and adaptation for each new employee.
• The opportunity to earn up to an additional 1,000 EUR per month, depending on the level of expertise, which will be included in the annual bonus, by participating in the company's activities.
• Access to the corporate training portal, where the entire knowledge base of the company is collected and which is constantly updated.
• Bright corporate life (parties / pizza days / PlayStation / fruits / coffee / snacks / movies).
• Certification compensation (AWS, PMP, etc).
• Referral program.
• English courses.
• Private health insurance and compensation for sports activities.

Join us!