Research Scientist, AI /ML Biologics (12 months)

Role Overview

In this role, you will develop sequence‑aware predictive models to support the design and prioritization of nucleic acid-based therapeutics that modulate RNA processing and expression. You will extend these approaches across multiple oligonucleotide and conjugated modalities.

You will also contribute to AI/ML‑enabled biologics discovery, supporting modeling of antibody-antigen sequence, structure, and interactions. The role supports the development of cross‑modality computational design and decision‑support platforms spanning nucleic acid and protein‑based therapeutics.

Key Responsibilities

• Design and implement advanced AI/ML methods for de novo protein and antibody discovery, including fine‑tuning protein language models and developing generative protein design workflows.
• Develop, deploy, and scale machine learning solutions to enable multi‑objective optimization across biologic and nucleic acid therapeutic modalities, including antibodies, conjugates, and related platforms.
• Develop and extend sequence‑aware machine learning models to prioritize oligonucleotide designs based on predicted RNA modulation outcomes across multiple targets and chemical modalities, including chemically modified ASOs, hybrid designs, and conjugated formats.
• Build and maintain a reproducible end‑to‑end computational framework encompassing data ingestion, feature engineering, model training, validation, and deployment in support of therapeutic design programs.
• Curate, integrate, and harmonize internal and external datasets, including literature‑derived sources, and define robust sequence‑ and structure‑based features such as thermodynamics, target accessibility, sequence motifs, secondary structure, and broader biological context.
• Establish benchmarks, validation strategies, and prospective testing workflows to evaluate model accuracy, robustness, and scalability, working in close partnership with experimental and translational teams.
• Evaluate, adopt, and integrate open‑source and proprietary tools to improve modeling workflows and accelerate data‑driven decision making.
• Maintain a clean, well‑documented, production‑ready codebase and provide technical documentation and user guidance for cross‑functional scientific teams.
• Perform additional related responsibilities as needed to support computational and discovery initiatives.

Required Skills & Education

• PhD in Computational Chemistry, Computational Biology, Machine Learning, Biomedical Engineering, Chemical Engineering, or a related quantitative field, with 3+ years of directly relevant industry experience.
• Strong background in nucleic acid therapeutics chemistry and protein‑ or antibody‑based biologics design and characterization.
• Demonstrated experience in computational modeling of protein-protein or antibody-antigen interactions, including sequence‑ and structure‑based approaches.
• Deep expertise in probabilistic and deep learning methodologies, including architectures such as RNNs, GNNs, Transformers, NLP‑inspired sequence models, and generative AI techniques.
• Advanced programming skills in Python (and working knowledge of R and SQL), with hands‑on experience using modern ML/DL frameworks such as PyTorch, TensorFlow, scikit‑learn, or JAX.
• Experience developing machine learning models for DNA, RNA, and/or protein sequences, including language models, structure prediction, and design‑oriented modeling.
• Familiarity with large‑scale compute environments, cloud infrastructure, databases, and ML systems deployed in production settings.
• Experience with data and ML infrastructure tools such as cloud platforms (e.g., AWS), version control systems, CI/CD workflows, and containerization technologies.
• Strong communication and collaboration skills, with the ability to work effectively in multidisciplinary teams spanning chemistry, biology, and data science.
• A collaborative mindset and a demonstrated commitment to continuous learning, scientific rigor, and technical excellence.