AI/LLM Engineer

• Design and implement advanced AI workflows and agent-based architectures

• Apply and fine-tune RAG (Retrieval-Augmented Generation) pipelines

• Craft high-quality prompts and experiment with prompt engineering strategies

• Work with Langchain and other LLMOps tools to optimize chatbot performance

• Analyze user behavior to improve system accuracy and naturalness

• Collaborate closely with engineers and product teams to test and deploy improvements

• Stay ahead of trends in LLMs and conversational AI

• Proven experience with GPT or other large language models

• Hands-on experience building AI agents and agentic workflows

• Deep understanding of RAG and its real-world implementation

• Strong Python skills and familiarity with vector databases

• Experience with Langchain and LLMOps best practices

• Excellent English skills for prompt writing and collaboration

• Analytical mindset and proactive approach to experimentation

• Passion for AI and continuous learning

HeadHunter