Senior AI Engineer

x1F is a company operating in multiple locations including Warszawa, Budapest, Ateny, Bukareszt, and Belgrad, Poland. The role involves working on AI and agentic systems with a focus on Large Language Models, Retrieval-Augmented Generation architectures, and cloud platforms, particularly Microsoft Azure.

• Strong hands-on experience with AI/ML systems, especially Large Language Models, NLP, and agent-based architectures.
• Deep understanding of LLM capabilities and limitations, including prompt engineering, fine-tuning, self-hosted models, and explainable AI.
• Experience building Retrieval-Augmented Generation systems and integrating structured and unstructured data.
• Strong experience designing AI solutions on Microsoft Azure cloud platform.
• Experience with CI/CD pipelines and automation tools such as Jenkins or Bitbucket.
• Strong programming skills in Python and/or Java.
• Experience with SAP is a significant advantage.
• Senior-level, structured and self-driven working style with pragmatic, prototype-first approach and strong ownership.
• Ability to explain complex AI concepts clearly to technical and non-technical stakeholders.
• English language proficiency is required; German is a strong advantage with supported learning opportunities.

Design Agentic Systems:

• Design AI agent architectures, define boundaries between agentic and non-agentic components, and ensure alignment with target architecture, workflows, and compliance requirements.

Build & Orchestrate Agents:

• Implement and orchestrate AI agents, integrate them into existing process landscapes, define interaction points between multiple agents and systems, and ensure reliable deployment using containerized environments such as Docker.

Integrate LLMs & Prompt Systems:

• Select and integrate suitable LLM providers, design prompts, system instructions, and guardrails, and build interfaces and tools for robust AI interactions.

Develop RAG Solutions:

• Design and implement Retrieval-Augmented Generation architectures, connect relevant data sources, and ensure high-quality, up-to-date knowledge retrieval across systems.

Evaluate & Improve AI Systems:

• Define evaluation frameworks and KPIs such as accuracy, latency, cost, and reliability, design test datasets, validate system behavior with stakeholders, and continuously improve models and architectures.