PhD Residency - Machine Learning, Drug Discovery - SandboxAQ

Residencies at SandboxAQ

The SandboxAQ Residency Program is an excellent, paid opportunity for graduate students to have industrial impact. Residents work within all of the teams at SandboxAQ on a variety of projects, and each have a unique experience depending on the work their team is focused on, as well as their own interests, skills, and goals. During their time with the program, we encourage residents to contribute to publications, attend conferences, and pursue their professional development. In addition to technical work, community is very important to us and we provide space and events to network and socialize with others in the program, as well as the SandboxAQ community as a whole.

AQBioSIm Team Charter

The AQBioSim team develops AI and quantum solutions for computational science, with a near-term focus on drug design. We seek revolutionary impact on human health, the environment, and the economy. AQBioSim Residents will develop and implement novel physics-based, AI, quantum, and quantum-inspired algorithms for drug design and beyond. Working closely with a focused team of PhDs, MBAs, engineers, and product experts, you will confront hard social problems, make business impact, and improve lives.

As our newest Machine Learning Resident, here are some of the things you may work on

As a machine learning resident supporting the drug discovery group, you will work closely with a cross functional group of machine learning engineers, software engineers, and computational chemists to build the next generation of AI first tools to impact the development of new medicines. Utilizing your expertise in software engineering, machine learning, and data science, you will:

• Contribute to ongoing research in the development of foundation models applied to areas in drug discovery
• Develop novel ML methods for forcefield improvement
• Create and improve machine learning methods applied to drug discovery problems
• Develop innovative ML methods to predict functional characteristics and properties of small molecules and biological systems for rational structure-based drug design

Qualifications

• Currently enrolled or recently completed a STEM PhD Program in relevant technical field
• Preferred: coursework / qualifying exams are complete
• Proficiency in Python
• Experience developing models using modern machine learning and deep learning frameworks and libraries (e.g. PyTorch, TensorFlow, JAX, Scikit-Learn)
• Experience with a Unix-style terminal environment
• Experience in one or more of the following ML applications to drug discovery or materials science: chemical space exploration, reinforcement learning, active learning, generative methods for chemistry, ML force fields, crystal structure prediction, reaction pathway prediction, QSAR, similarity search, chemical space visualization, ADME ML predictions, PK ML predictions, chemical clustering, knowledge graphs, foundation models

Nice-to-Have

• Domain expertise in at least one of the above key areas, as indicated by at least one relevant high-impact publication.

Other Details

• Location: Remote in North America
• Start date: Year-round, on a rolling basis
• Duration:  4-6 months