AI Agent Middle/Senior Developer

Itransition is hiring an AI Agent Developer to join their AI team, working on AI systems with modern agent technologies. The role involves working remotely or from various cities including Warsaw, Gdańsk, Wrocław, Vilnus, and Poznań in Poland.

• Strong Python skills and proven production experience with Agentic ecosystems
• Experience with embeddings and vector search
• Knowledge of prompt and context engineering
• Familiarity with RAG, CRAG, GraphRAG
• Experience with LangChain, LangGraph, CrewAI
• Skills in agent testing and verification
• Experience with AI-assisted coding models and tools
• Strong analytical and problem-solving mindset
• Ability to clearly communicate findings and trade-offs
• Ownership of tasks from research to implementation
• Curiosity and willingness to explore new approaches
• English proficiency sufficient for technical and business communication with native speakers

Nice to have:

• Experience with Autonomous Agents and Deep Agents
• Knowledge of model types and capabilities (Thinking, Multimodal models)
• LLMOps experience
• GenAI Observability
• Memory management and prompt caching
• Model governance and data governance (Responsible AI)
• Basic knowledge of cloud infrastructure
• Familiarity with agentic patterns
• Understanding of integration mechanics (MCP, AA-protocol)
• Basic understanding of machine learning fundamentals including supervised learning, feature engineering, model evaluation, overfitting, regularization, and cross-validation
• Knowledge of statistical methods and probability theory

• Develop, implement, and optimize AI agents capable of autonomous decision-making, reasoning, and tool usage in real-world scenarios
• Build and maintain pipelines for agent planning, memory, retrieval, and multi-step task execution
• Integrate LLMs, vector stores, APIs, and external tools to enable complex agent behaviors
• Design and refine prompting strategies, reasoning chains, and agent policies to improve reliability and accuracy
• Implement evaluation frameworks for agent performance, safety, and robustness across diverse tasks
• Monitor agent behavior in production, troubleshoot failures, and continuously improve quality of outputs
• Optimize inference pipelines for speed, cost efficiency, and model/tool selection