AI Engineer (Agentic AI / LLM)

Quick Facts

• Role: AI Engineer (Agentic AI / LLM)

• Work mode: Remote – Europe

• Hours: Availability for US–Europe time zone overlap until ~18:00–19:00 CET

Description

Join a hands-on role building and deploying agentic AI workflows powered by LLMs. You will develop agent tools, prompt pipelines, retrieval mechanisms, and automated evaluation frameworks while partnering with senior AI engineers and backend teams to deliver production-ready solutions.

Responsibilities

• Build, configure, and maintain AI agent workflows, prompt chains, and tool/function-calling integrations within the AgentQ ecosystem

• Develop REST API connectors, backend services, and lightweight data retrieval pipelines

• Implement and optimize RAG pipelines, embeddings, and vector database integrations

• Design and implement automated test suites, benchmark datasets, and evaluation frameworks for accuracy, response quality, latency, and guardrail compliance

• Debug edge cases, monitor production executions, and continuously improve prompts, retrieval strategies, and fallback mechanisms

• Maintain technical documentation covering architectures, API interfaces, testing, and operational runbooks

• Collaborate to support production deployments and deliver reliable AI automation capabilities

Requirements

• 2+ years of hands-on experience in Python for software engineering, backend development, or applied AI/LLM engineering

• Practical experience building LLM-powered applications, RAG pipelines, or AI agent workflows

• Familiarity with agentic AI frameworks such as LangChain and LlamaIndex, and LLM APIs (OpenAI, Anthropic, or Mosaic AI)

• Backend fundamentals: REST API development with Python (FastAPI or Flask), JSON schemas, API integrations, asynchronous programming, and error handling

• Git and collaborative development workflows

• Understanding of vector databases, embeddings, semantic search, and retrieval techniques

• Basic experience with SQL and cloud/data platforms such as Databricks, AWS, or Azure

• Strong analytical and troubleshooting skills using evaluation metrics and user feedback

• Good communication and ability to collaborate effectively with distributed teams

• Comfortable working remotely with US–Europe time zone overlap until ~18:00–19:00 CET

Benefits

• Build real-world agentic AI workflows (not standalone prototypes)

• Improve agent reliability, performance, and scalability through systematic testing and evaluation

• Work with experienced AI and backend engineers to bring next-generation AI automation into production

Nice to Have

• Production deployment and maintenance of LLM-powered applications

• Experience with LLM evaluation, observability, tracing, and monitoring

• Understanding of AI safety, guardrails, structured outputs, and hallucination mitigation

• Docker and CI/CD experience

• Exposure to multi-agent architectures and orchestration patterns