AI Research Scientist - GNN / Foundation Models

Job Description

Job Description

Radical AI, Inc.  is an artificial intelligence company that is accelerating scientific research & development. We are at the forefront of innovation in the field of materials R&D, a critical driver for advancing our most cutting-edge industries and shaping the future. Breaking away from the traditionally slow and costly R&D process, Radical AI leverages artificial intelligence and machine learning to pioneer generative materials science. This innovative field blends AI, engineering, and materials science, revolutionizing how materials are created and discovered. Radical AI's approach speeds up R&D and addresses global challenges, setting new benchmarks in technology and sustainability.

The opportunity

As an AI Researcher focused on the development of our foundation model, you will be at the forefront of integrating advanced ML techniques with materials modeling to create a generalizable, robust, and scalable universal ML interatomic potential capable of accelerating materials discovery. Your work will play a critical role in enabling self-driving labs and advancing AI-driven materials science.

Your expertise will contribute to the broader research community through publications in top-tier AI / ML venues like NeurIPS, ICML, ICLR, and our company blog, alongside active participation in conferences and workshops. This role offers the unique opportunity to mentor and guide junior members of our technical team and research interns, fostering a culture of growth and innovation.

Positions are available at various levels of seniority : Senior, Staff, and Principal.

Mission

• Develop scalable MLIP frameworks capable of representing diverse chemical systems with high fidelity.
• Innovate and implement state-of-the-art machine learning models, such as graph neural networks, equivariant architectures, or hybrid approaches for interatomic potential development.
• Curate and integrate large-scale datasets from first-principles calculations (e.g., DFT) and experimental sources.
• Explore active learning and automated data acquisition workflows for efficient dataset expansion.
• Address challenges of scalability, generalizability, and transferability in MLIP designs.
• Optimize training and inference pipelines to leverage high-performance computing resources effectively.
• Contribute to the AI and materials science research community through publications and active engagement in top-tier AI / ML venues like NeurIPS, ICML, ICLR, and our company blog, alongside active participation in conferences and workshops.
• Tackle challenging problems with new and different ideas, creativity and contrarian thinking.
• Mentor and guide junior team members and interns, promoting an environment of continuous learning and innovation.

About you

Pluses

What we offer

Radical AI is committed to equal employment opportunity regardless of race, color, ancestry, national origin, religion, sex, age, sexual orientation, gender identity and expression, marital status, disability, or veteran status.