PhD Position in Agentic AI for Materials Discovery
Develop AI-driven experimental workflows to bridge the gap between AI-proposed materials and real-world synthesis and characterization.
Best for:Best for interdisciplinary PhD candidates with a background in computer science, AI, physics, chemistry, or materials science, who are eager to merge agentic AI with laboratory automation and experimental materials research.
Overview
This PhD position at DIFFER’s Autonomous Energy Materials Discovery (AMD) group focuses on integrating agentic AI systems with laboratory automation to accelerate materials discovery. The successful candidate will design and implement AI-driven experimental workflows that translate AI-generated alloy compositions into executable synthesis and characterization plans. The role involves hands-on laboratory work, including high-throughput synthesis using nanoparticle printers and sample characterization via micro-XRF and SEM. The project is collaborative with an industrial partner specializing in generative AI for materials, and the candidate will contribute to a FAIR-aligned dataset to improve AI model development. Training and technical support for instrumentation are provided, making this an ideal opportunity for interdisciplinary researchers with strong programming skills and a passion for AI-driven experimentation.
What you'll do
- Design and implement an agentic AI-driven experimental workflow that converts AI-proposed alloy compositions into executable synthesis and characterization plans, ensuring quality control, traceability, and structured reporting.
- Conduct high-throughput synthesis of material libraries using a nanoparticle printer, with precise control over composition and deposition conditions.
- Characterize samples using micro-XRF composition mapping and SEM, developing reproducible Python pipelines to extract composition, homogeneity, and morphology metrics.
- Develop and maintain a structured, FAIR-aligned dataset capturing successful, partial, and failed experimental outcomes, including realizability labels, to support AI model development.
- Integrate AI agents with project databases, analysis tools, and reporting systems to ensure traceability and reproducibility of the experimental workflow.
- Write well-tested, reproducible research software and contribute to publications and conferences.
- Complete and defend a PhD thesis within four years.
Requirements
Degree required: Master's degree in computer science, artificial intelligence, data science, physics, chemistry, materials science, or a related field.
Degree offered: PhD
Language: English; proficiency required for effective collaboration in a multidisciplinary team.
Instruction: English
- Strong Python programming skills and proficiency in software engineering practices (e.g., Git, testing, reproducible code).
- Experience or strong interest in agentic AI systems, including LLM-based agents, workflow automation, and database/data pipeline integration.
- Motivation to apply AI in laboratory settings and willingness to learn hands-on materials synthesis and characterization.
- Hands-on, meticulous working style with a good command of English.
- No specific nationality or residency restrictions mentioned.
- No age limits or prior experience caps specified.
Funding & terms
How to apply
Deadline: 2026-10-25
Applicants should submit their CV, a motivation letter, and a list of references through the application portal. Additional documents may be requested depending on the application review process.
- CV
- Motivation letter
- List of references
Create a free profile to unlock your personal match score, the full requirements, funding details and how to apply — in English or Persian.