AI Research Scientist

The role

You will develop new machine learning methods to predict how drug compounds behave in the human body. This involves formulating research questions, designing experiments, and developing novel model architectures to solve complex scientific problems.

What you will do

• Own research problems in predictive toxicology, drug safety, and computational biology from hypothesis to validation.
• Develop and evaluate novel deep learning architectures and training methods.
• Investigate representations connecting molecular structure, biological targets, and clinical outcomes.
• Develop approaches for learning from heterogeneous, sparse, noisy, and partially observed scientific datasets.
• Explore methods for cross-domain and out-of-distribution generalization.
• Design rigorous experiments, benchmarks, ablations, and evaluation frameworks.
• Develop methods for uncertainty estimation, calibration, and applicability-domain assessment.
• Investigate approaches for making model predictions more mechanistically interpretable.
• Explore multimodal and foundation-model approaches.
• Work with AI/ML and data engineers to translate research into scalable modeling systems.

Required qualifications

• PhD in machine learning, artificial intelligence, computer science, computational biology, computational chemistry, applied mathematics, statistics, or equivalent demonstrated research experience.
• Strong research track record demonstrated through publications, novel methods, significant open-source research, or technically substantial research projects.
• Deep understanding of modern machine learning and deep learning.
• Hands-on experience developing and evaluating models in PyTorch, JAX, or equivalent frameworks.
• Experience with one or more of: graph neural networks, transformers, representation learning, multimodal learning, generative modeling, self-supervised learning, probabilistic modeling, or foundation
• Strong experimental instincts and experience designing controlled evaluations, ablations, and reproducible research.
• Ability to reason carefully about dataset construction, leakage, confounding, generalization, and evaluation methodology.
• Ability to independently identify important research questions and carry projects from initial hypothesis through rigorous experimental results.
• Strong written and verbal communication skills.

Nice to have

• Computational biology, computational chemistry, cheminformatics, or drug discovery.
• Molecular machine learning or geometric deep learning.
• Biological foundation models.
• Multimodal scientific machine learning.
• Causal inference or mechanistic modeling.
• Uncertainty quantification and model calibration.
• Out-of-distribution/generalization research.
• Active learning or experimental design.
• Pharmacology, toxicology, PK/PD, or translational science.
• Working with large scientific or biomedical datasets.

Benefits

• Competitive compensation
• Meaningful equity participation
• Opportunity to work on foundation-level ML systems
• Ownership over model design and training strategy
• Close collaboration with data, AI/ML, infrastructure, and scientific teams
• High autonomy, low bureaucracy
• Flexible remote or hybrid work arrangements

Before you apply

• Submit your resume and a brief note describing your experience training large-scale models.
• Links to GitHub repositories, papers, or technical write-ups are encouraged.

About the company

Absentia Labs is building mechanistic AI models to predict how drug compounds will behave in the human body before costly preclinical and clinical studies. The platform integrates molecular properties, exposure, biological context, experimental evidence, and machine learning.