Research Engineer (AI Agents & LLM Systems)

We are seeking a Research Engineer to help develop intelligent agent-based systems powered by large language models.

This role sits at the intersection of applied research and engineering. You will explore emerging approaches, turn promising ideas into working prototypes, and help build reliable systems capable of reasoning, using tools, retrieving information, and completing complex tasks.

What You’ll Do

• Research and prototype new approaches for LLM-powered agents.
• Design systems that combine language models with tools, memory, retrieval, planning, and structured workflows.
• Build experiments and evaluation frameworks to measure agent quality, reliability, and performance.
• Investigate challenges such as hallucination, long-horizon task completion, context management, and error recovery.
• Translate research findings into practical, maintainable implementations.
• Analyse experimental results and use them to guide technical decisions.
• Keep pace with relevant developments in language models, agent architectures, and evaluation techniques.
• Share findings clearly through technical documentation, demonstrations, and discussions.

What We’re Looking For

• Hands-on experience developing or researching systems based on large language models.
• Strong software engineering and experimental development skills.
• Experience building AI agents, multi-step LLM workflows, or tool-using applications.
• An understanding of techniques such as prompting, retrieval-augmented generation, structured outputs, model evaluation, and orchestration.
• The ability to design controlled experiments and interpret results critically.
• Confidence working with ambiguous research questions and turning them into testable ideas.
• Clear technical communication and a collaborative approach to problem-solving.

Experience in any of the following areas would be useful:

• Agent planning and reasoning.
• Tool use and function calling.
• Multi-agent systems.
• Memory and context management.
• Retrieval and knowledge-grounded generation.
• LLM evaluation and benchmarking.
• Model observability and tracing.
• Safety, robustness, and guardrails.
• Fine-tuning or model adaptation.
• Human–AI interaction.

This position offers the chance to work on technically challenging problems at the forefront of applied AI. You will have room to investigate new ideas while remaining closely involved in the engineering required to make agentic systems useful, dependable, and measurable.

If you are excited by the challenge of turning advances in LLMs and AI agents into robust real-world systems, apply now or email [email protected]

By applying to this role you understand that we may collect your personal data and store and process it on our systems. For more information please see our Privacy Notice (https://eu-recruit.com/about-us/privacy-notice/)