Staff/Principal AI Scientist - Virtual Tissue

About Absci

Absci is a clinical-stage biotechnology company advancing novel therapeutics using generative AI. Our Integrated Drug Creation™ platform combines cutting-edge AI models with a synthetic biology data engine, enabling the rapid design of innovative therapeutics that address challenging therapeutic targets.

About the role

Absci is looking for an expert Staff/Principal AI Scientist to advance and deploy virtual tissue models. We are looking for exceptional contributors with backgrounds in deep learning and systems biology to develop innovative approaches for discovering therapeutic targets.

Absci’s computational teams (including its AI Scientists) develop and validate software platforms for disease biology, target discovery, and antibody design. These tools are then deployed in partnership with the full Drug Creation team, including disease biologists, protein engineers, and screening scientists, to expand our growing therapeutic pipeline.

The ideal Staff/Principal AI Scientist candidate will:

• Be passionate about solving core problems in biology with a direct path from fundamental science to patient impact.

• Use their expertise to influence the AI team's research agenda, while maintaining high levels of responsibility and accountability for their work;

• Demonstrate their curiosity about the problems we are attempting to solve by developing proficiency in disciplines that fall outside their own areas of expertise, constantly increasing the scale and impact of their contributions.

• Invest in ensuring their work is accessible and interpretable to scientists with other domain expertise.

• Set strategic direction, by leading development and communication of research, insights and strategies across the organization.

This is a remote position, with the option to work onsite at our New York City office or our Vancouver, WA headquarters if within commuting distance

Why Absci’s AI team?

Absci offers AI Scientists a unique opportunity to both develop novel, cutting edge machine learning models and apply these models directly to identify novel targets, unlocking previously intractable disease interventions, and to generate candidate antibody therapeutics. In particular we:

• Provide our AI Scientists with access to industry-leading compute resources, enabling large-scale experimentation for model training and deployment

• Maintain our own Wet Lab, enabling AI Scientists to validate novel modeling methods via rapid design > build > test > learn cycles

• Developed and are growing our own pipeline of clinical-stage assets, enabling AI Scientists to see their work directly translated into therapeutic impact for patients

Key Responsibilities

• Develop, adapt, and deploy deep learning models that predict the intra- and intercellular signaling effects of potential therapeutic interventions

• Develop data sourcing strategies to train and validate virtual tissue models

• Collaborate closely with cross-functional teams comprising Disease Biologists, Structural Biologists, Computational Biologists, and Wet Lab scientists to define and address the problem space within specific indications

• Develop in silico and in vitro validation approaches to iteratively improve design and evaluation methodologies

• Communicate and present experimental results in a manner that is accessible to audiences with highly-diverse backgrounds, driving discussions that lead to high-quality, informed decision-making and program progression

• Deliver and publish high-impact research that advances Absci’s position as a leader in AI-guided antibody therapeutic discovery.

• Actively develop organizational talent through coaching and mentoring other Scientists and Engineers.

Qualifications

• PhD or equivalent experience in Machine Learning, Computer Science, Computational Biology, Computational Chemistry, Biophysics, or a related field

• 6+ years of experience (Staff) or 8+ years of experience (Principal)

• Seasoned deep learning expert with a strong background in several of the following areas: biological world models, mathematical biology, systems biology, disease biology, computational biology/multi-omics, experiment design to generate and/or handling intra- and intercellular perturbation datasets

• Fluency in Python and PyTorch

• Expertise in large-scale model architecture design and training

• Mastery of proper scoring rules, validation metrics for highly imbalanced biological datasets, and active learning paradigms.

• Demonstrated ability to work collaboratively in an ambitious, fast-paced, interdisciplinary environment

• Demonstrated experience presenting complex technical work to diverse audiences

• Strong publication record in respected, high-impact journals and conferences