AI Engineer - Agentic Systems

Reply specialises in designing and implementing solutions based on new communication channels and digital media. Structured as a network of highly specialised companies, Reply supports leading European industrial groups in sectors such as Telco & Media, Industry and Services, Banking and Insurance, and Public Administration, helping define and develop business models enabled by new paradigms such as AI, Cloud Computing, Digital Media, and the Internet of Things. Reply’s services include Consulting, System Integration, and Digital Services.

• Bachelor’s or Master’s degree in Computer Science, Artificial Intelligence, Data Science, Software Engineering, or a related technical field.
• Strong engineering skills in Python and/or JavaScript/TypeScript, including building services, APIs, packages, tests, and production-ready code.
• Hands-on experience with LLMs, NLP, embeddings, RAG, prompt engineering, structured generation, and agentic workflows.
• Experience with at least one modern LLM or agent orchestration framework such as LangGraph, Microsoft Agent Framework, LangChain, LlamaIndex.
• Familiarity with cloud platforms, preferably Azure or AWS, including services like Azure OpenAI, Azure AI Foundry, AWS Bedrock, serverless services, containers, storage, and identity/security concepts.
• Experience using modern AI engineering tools such as GitHub Copilot, Cursor, Claude Code, Codex or similar in daily development.
• Very good communication skills in English and Polish.
• Open to hybrid work mode with 1 day per month at the office in Katowice.

• Design and build agentic AI systems using modern LLM platforms such as Azure OpenAI and AWS Bedrock.
• Develop applications and AI workflows that integrate LLMs into cloud-native enterprise applications.
• Build and orchestrate AI agents using frameworks and patterns such as LangGraph, Microsoft Agent Framework, LangChain, LlamaIndex or similar tools.
• Transform research ideas, proof-of-concepts, and emerging AI capabilities into practical enterprise-grade solutions.