Senior Staff Scientist; AI Self-Driving Labs

Date Posted: 03/31/2025

Req : 46987

Faculty/Division: Faculty of Arts & Science

Department: Acceleration Consortium

Campus: St. George (Downtown Toronto)

Description:

The Acceleration Consortium (AC) at the University of Toronto (U of T) is leading a transformative shift in scientific discovery that will accelerate technology development and commercialization. The AC is a global community of academia, industry, and government that leverages the power of artificial intelligence (AI), robotics, materials sciences, and high-throughput chemistry to create self-driving laboratories (SDLs), also called materials acceleration platforms (MAPs).

These autonomous labs rapidly design materials and molecules needed for a sustainable, healthy, and resilient future, with applications ranging from renewable energy and consumer electronics to drugs. AC Senior Staff Scientists will advance the field of AI-driven autonomous discovery and develop the materials and molecules required to address society's largest challenges, such as climate change, water pollution, and future pandemics.

The Acceleration Consortium (AC) promotes inclusive research environment and supports the EDI priorities of the unit.

The Acceleration Consortium received a $200M Canadian First Research Excellence Grant for seven years to develop self-driving labs for chemistry and materials, the largest ever grant to a Canadian University. This grant will provide the Acceleration Consortium with seven years of funding to execute its vision.

The AC is developing seven advanced SDLs. These include:

• SDL0 - A central AI and Automation lab to support all the SDLs
• SDL1 - Inorganic solid-state compounds for advanced materials and energy
• SDL2 - Organic small molecules for sustainability and health
• SDL3 - Medicinal chemistry for improving small molecule drug candidates
• SDL4 - Polymers for materials science and biological applications
• SDL5 - Formulations for pharmaceuticals, consumer products, and coatings
• SDL6 - Biocompatibility with organoids / organ-on-a-chip
• SDL7 - Synthetic scale-up of materials and molecules (University of British Columbia partner lab)

• Agentic and sequential decision‑making for autonomous experimentation, including active learning and optimal experimental design
• Generative and probabilistic modeling, including uncertainty estimation, risk‑aware prediction, and data‑efficient learning
• Continual, transfer, and meta‑learning, with emphasis on sim‑to‑real and real‑to‑sim generalization
• Applied machine learning on real‑world experimental or industrial data, including multivariate time‑series and noisy, sparse, or incomplete datasets
• Close collaboration with experimental scientists, translating scientific objectives into ML‑driven or autonomous systems

The Senior Staff Scientists will work with a diverse team of leading experts at U of T, including Faculty and Staff Scientists such as:
Professors Anatole von Lilienfeld, Kourosh Darvish, Florian Shkurti, Animesh Garg, Alán Aspuru‑Guzik, Chris Sutton, Oleksandr Voznyy, and more.

The Senior Staff Scientists involved in the AC are highly skilled and experienced researchers who will work independently to develop the AI and automation technologies required to build robust and scalable self‑driving labs, manage these SDLs, and design and implement research programs (based on the direction of the AC’s scientific leadership team) that leverage the SDL platforms to discover materials and molecules.

Moreover, the Senior Staff Scientists will work collectively, sharing knowledge among each other, faculty, and trainees.

This role will report to the Academic Director and Executive Director of the Acceleration Consortium.

The components and duties of the work include:

• SDL and Automation Development

Working with the AC community, including faculty and partners to determine the required capabilities of the SDLs to be built. Developing the plans for SDLs that will meet user requirements and designing novel instruments for automated material synthesis…