AI Engineer (Python / AWS / RAG)

You will join a team building Generative AI solutions as part of an AI Center of Excellence (CoE) initiative for our client. The project focuses on developing GenAI-based workflows and agent architectures that automate work with unstructured data such as emails, documents, and web content. The solutions are developed in environments including AWS and Microsoft 365, using modern GenAI platforms and libraries. The engagement is initially planned for a minimum of 6 months, with the potential to expand both the team and project scope. You will work in an international environment as part of a team developing AI solutions used across the entire organization.

• Minimum 10 years of experience in software engineering
• Minimum 2–3 years of experience in Generative AI projects
• Very strong Python skills
• Experience working with LLM APIs (e.g., OpenAI, Azure OpenAI, Gemini, Anthropic)
• Experience with prompt engineering, building context for LLM models, and grounding strategies
• Practical experience with Retrieval-Augmented Generation (RAG) and working with unstructured documents (PDFs, emails, Office documents, websites)
• Experience building REST APIs and integrating systems
• Experience with AWS, especially Lambda, Bedrock, Step Functions, API Gateway, IAM
• Experience with GenAI monitoring and observability tools (e.g., LangSmith, Dynatrace, CloudWatch)
• Understanding of AI governance, data privacy, and security concepts
• Excellent communication skills in Polish and English

Nice to have:

• Experience with Model Context Protocol (MCP) or Google A2A
• Experience with Microsoft Copilot extensibility
• Experience with Intelligent Document Processing / OCR
• Experience with traditional Machine Learning

• Designing and developing Generative AI solutions based on prompt engineering, context engineering, and Retrieval-Augmented Generation (RAG) architecture
• Building AI agents and interoperable agent-based workflows
• Developing pipelines for processing unstructured data (e.g., emails, documents, websites)
• Integrating AI models with internal and external systems via APIs
• Building reusable AI services and components
• Designing and implementing frameworks for testing LLM models
• Creating test suites to detect model quality degradation or prompt changes
• Ensuring security of AI solutions (protection against prompt injection, jailbreaks, etc.)
• Collaborating with the AI Center of Excellence on architecture, scalability, and AI governance
• Documenting solutions and preparing user stories in an Agile environment