We are looking for an AI Engineer to join a product engineering team focused on introducing LLM-based capabilities into enterprise software and building systems such as MCP servers and agents. The role involves working on AI-driven product features, backend services, and integrations that connect models with tools and data in a scalable production environment.

Location: Serbia (relocation support available), Croatia, Poland, Portugal

Tasks:

• Design and develop AI-powered product features with a focus on LLM-based capabilities;
• Build and maintain MCP servers and agent-based components;
• Develop enterprise-grade web services and backend integrations;
• Work with tools, data sources, and model interfaces across cloud environments;
• Collaborate with engineering teams to deliver production-ready AI solutions.

Requirements:

CORE

• AI Engineer profile with strong SDE background;
• Proficiency in C# or Python;
• Knowledge of Model Context Protocol (MCP) for connecting tools and data into models;
• Experience in developing enterprise-grade web services;
• Experience working with cloud platforms such as Azure, AWS, or GCP.

Nice to have

• Hands-on experience with LLM and RAG engineering, including retrieval design, chunking, vector stores, and structured outputs, using tools such as OpenAI, LangChain, or LlamaIndex;
• Experience in building and orchestrating agentic systems that call tools and reason over retrieved context, using frameworks such as LangGraph or AutoGen, and OpenAI tool calling or the Responses API;
• Familiarity with LLM evaluation and observability tools such as LangSmith or Langfuse;
• Experience with guardrails and security measures such as prompt injection defense and output validation.