Middle AI / Agent Engineer

This is a remote position.

No model training. Just solid, reproducible AI solutions built by a practitioner who thinks systematically and knows how to get consistent output from LLMs.

• Write, test, validate, and iteratively improve prompts and system instructions until results are stable and reproducible;
  
• Build and configure AI agents – tool-use, memory, multi-step workflows;
  
• Implement RAG pipelines and connect LLMs to external data sources and APIs;
  
• Write integration and automation code (Python, Node.js, or any scripting language);
  
• Evaluate AI output quality in a structured way – accuracy, reliability, security and cost;
  
• Compare models (OpenAI, Anthropic, Gemini etc) and recommend the right one for the task;
  
• Monitor solutions in production, catch failures, and improve performance;
  
• Stay current with LLM ecosystem - new models, tools, and frameworks – and apply relevant findings to your work.
  

Requirements

• Hands-on experience with LLMs and prompt engineering – systematic work, not occasional ChatGPT usage;
  
• Experience building and configuring AI agents (planning, tool-use, memory);
  
• Working knowledge of LLM APIs – OpenAI, Anthropic, Google, or similar;
  
• Ability to write code in at least one scripting language for automation and integration tasks;
  
• Understanding basic AI evaluation techniques;
  
• Strong analytical and problem-solving mindset with attention to detail – able to explain why a solution was chosen;
  
• English B2+ (written and spoken).
  

• Experience with RAG, vector databases and other retrieval/ranking techniques;
  
• Multi-agent orchestration – LangChain, LangGraph or similar;
  
• No-code / low-code automation experience;
  
• Experience with STT / TTS integrations;
  
• Understanding of MCP and agent protocols;
  
• Cloud AI deployments – Amazon Bedrock or Azure OpenAI;
  
• Familiarity with monitoring and observability tools for AI system.
  

Benefits