PhD Position: Agentic AI-Driven Experiments Materials Discovery

DIFFER:
Science for future energy

At the Dutch Institute for Fundamental Energy Research (DIFFER) we work on a future in which clean energy will be available to everybody, anywhere in the world. DIFFER’s mission is to perform leading fundamental research on materials, processes, and systems for a global sustainable energy infrastructure.

Our research focuses on two major energy themes: fusion energy as a clean, safe and sustainable energy source and chemical energy. We work in close partnership with (inter) national academia and industry. DIFFER is one of the ten research institutes of the Dutch Research Council (NWO).

Within our institute physicists, chemists, engineers, and other specialists work together in multidisciplinary teams to accelerate the transition to a sustainable society. DIFFER’s workforce is currently composed of ~160 scientists (of which 60 guests and interns), supported by ~40 technicians and ~40 support staff members.

The global nature of the energy challenge is apparent from the international representation of our employees, who originate from over 30 different countries. To strengthen our commitment to diversity, we formed a task force to design, implement, and monitor diversity and gender equality initiatives.

PhD candidate who will join the Autonomous Energy Materials Discovery (AMD) group at DIFFER, working with researchers and engineers who are developing autonomous laboratory technologies.

The project is carried out in close collaboration with an industrial partner developing generative AI for materials discovery. The position suits a candidate with strong programming skills, from computer science, AI, physics, chemistry or materials science, who wants to work at the interface of agentic AI, laboratory automation and materials science, and who is happy to spend a substantial part of the project in the lab.

Roughly one third of your time will go to the digital workflow and two thirds to experimental work. Training and technical support are provided for all instruments. AI methods can propose material candidates far faster than they can be synthesized and validated. You will help close this gap by building an agentic AI workflow that turns AI-proposed alloy compositions into executable synthesis and characterization plans, and by generating the experimental evidence that shows which candidates can actually be made.

You will produce material libraries with a high-throughput nanoparticle printer and characterise them with micro-XRF and SEM. Successful, partial and failed outcomes will be captured in a structured, machine readable dataset to support AI model development and give feedback on material realizability.

In this position, you will have the following responsibilities:

• Design, implement, test and operate an agentic AI-driven experimental workflow that translates AI-proposed compositions into synthesis and characterization plans, supporting quality control, traceability and structured reporting.
• Carry out high-throughput synthesis of material libraries with a nanoparticle printer, with systematic control of composition and deposition conditions.
• Characterise samples with micro-XRF composition mapping and SEM, and develop reproducible Python pipelines to extract composition, homogeneity and morphology metrics.
• Develop and maintain a structured, FAIR-aligned dataset of successful, partial and negative outcomes, including realizability labels, and use it to support AI model development.
• Connect the AI agents to the project's data, planning and reporting steps, including databases and analysis tools, so that the path from candidate…