Senior AI Developer (LLM / RAG / Agentic AI)

About the role

Intetics, a technology company specializing in custom software development, team distribution, software quality assessment and digital solutions, is looking for a Senior AI Developer (LLM / RAG / Agentic AI) to join its team. The role suits a hands-on AI engineer (middle to senior level) who has delivered AI agents into production and can explain implementation challenges, failure cases and optimization approaches.

Key responsibilities

• Design, build and maintain LLM-based agents in production, both customer-facing and internal
• Build MCP servers on top of existing databases and production systems, and orchestrate multiple internal and external MCP servers under a unified agent framework
• Design and implement memory, context management and RAG architectures for production use
• Establish evaluation frameworks, handle edge cases and continuously improve agent performance after release
• Work within architectures combining databases, APIs, interfaces, agents and orchestration applications
• Develop AI solutions using Amazon Bedrock and/or Microsoft Foundry
• Collaborate with cross-functional teams to deliver scalable, reliable AI-powered products

Required profile

• 6+ years of overall experience as a software, ML or AI engineer
• 1.5-2+ years of hands-on experience with LLMs and AI agents in production
• Proven experience building and deploying LLM-based agents, including conversational AI and workflow automation agents
• Strong background in machine learning, Python development or data science
• Hands-on experience with Docker and CI/CD pipelines

Required skills

• Amazon Bedrock and/or Microsoft Foundry (Azure AI Foundry, Azure OpenAI)
• An agent framework such as LangGraph, LangChain, LlamaIndex, Semantic Kernel, AutoGen, Strands Agents or OpenAI Agents SDK
• Deep MCP expertise: building MCP servers, integrating external ones and orchestrating multiple services
• Production-grade RAG, memory and context engineering (embeddings, chunking, hybrid search, reranking, vector databases, short- and long-term memory)
• Agentic patterns such as ReAct, Planner-Executor, Reflection, Router, Supervisor, Multi-Agent Systems and Human-in-the-Loop
• LLM evaluation, guardrails, monitoring and iterative optimization
• Nice to have: fintech or regulated industry experience, broader AWS/Azure cloud expertise, and tools like LangSmith, Langfuse or Ragas