ABOUT US

Excelsior Sciences is a New York City–based startup at the forefront of technology-driven drug discovery. We combine cutting-edge advances in artificial intelligence, laboratory automation, and our proprietary chemistry platform to redefine how small-molecule leads are identified and optimized.
We are building a world-class team of scientists and engineers passionate about transforming therapeutic discovery. As a Machine Learning Scientist, you will play a key role in developing and scaling our computational platform, working at the exciting intersection of chemistry, biology, and AI. This is an opportunity to make a tangible impact in a fast-paced, collaborative environment where your ideas and expertise will directly shape the future of our technology and our mission.
Responsibilities:

WHAT WE’RE LOOKING FOR

We are seeking a senior-level scientist with deep expertise in machine learning applied to drug discovery and a demonstrated ability to translate computational methods into real-world impact. This role is ideal for someone who combines technical excellence with a collaborative mindset and a passion for advancing therapeutic discovery.

• PhD in Machine Learning, Computational Chemistry, Cheminformatics, Computer Science, or a related discipline.
• At least 3 to 5 years of hands-on experience applying machine learning in a drug discovery or cheminformatics context, with a track record of impactful contributions.
• Proven expertise with advanced methods such as Bayesian optimization, uncertainty quantification, generative models, and/or active learning in molecular design.
• Deep expertise in machine learning libraries and frameworks (e.g., PyTorch, scikit-learn, GPyTorch) and cheminformatics toolkits (e.g., RDKit, Open Babel).
• Strong understanding of molecular representations (SMILES, graphs, fingerprints) and familiarity with pharmaceutical and chemical datasets.
• Proficiency in Python and experience working in a collaborative, cross-disciplinary environment.
• Excellent communication skills, intellectual curiosity, and the ability to thrive in a fast-paced, mission-driven startup.

WHAT YOU’LL DO

• Design, implement, and refine machine learning models for molecular property prediction, generative chemistry, and active learning.
• Analyze and model large-scale molecular datasets to inform the selection of reagents and the design of libraries.
• Collaborate closely with synthetic chemists and automation engineers to translate computational insights into actionable laboratory strategies.
• Contribute to the development of scalable infrastructure and workflows for model training, evaluation, and deployment.
• Stay abreast of emerging methods and literature, proactively bringing innovative ideas into our discovery platform.
  Qualifications:

We are seeking a senior-level scientist with deep expertise in machine learning applied to drug discovery and a demonstrated ability to translate computational methods into real-world impact. This role is ideal for someone who combines technical excellence with a collaborative mindset and a passion for advancing therapeutic discovery.

• PhD in Machine Learning, Computational Chemistry, Cheminformatics, Computer Science, or a related discipline.
• At least 3 to 5 years of hands-on experience applying machine learning in a drug discovery or cheminformatics context, with a track record of impactful contributions.
• Proven expertise with advanced methods such as Bayesian optimization, uncertainty quantification, generative models, and/or active learning in molecular design.
• Deep expertise in machine learning libraries and frameworks (e.g., PyTorch, scikit-learn, GPyTorch) and cheminformatics toolkits (e.g., RDKit, Open Babel).
• Strong understanding of molecular representations (SMILES, graphs, fingerprints) and familiarity with pharmaceutical and chemical datasets.
• Proficiency in Python and experience working in a collaborative, cross-disciplinary environment.
• Excellent communication skills, intellectual curiosity, and the ability to thrive in a fast-paced, mission-driven startup