Research Scientist AI-ML Biologics

Job Description:

Candidates should have strong AI/ML expertise, a solid biology background, and exposure to peptide and antibody design. If all three are limited, please prioritize AI/ML candidates with oligonucleotide/RNA experience.

The Importance of the Role

The client is expanding its capabilities in antisense oligonucleotide (ASO) therapeutics, including phosphorodiamidate morpholino oligomers (PMOs) and emerging oligonucleotide modalities, while advancing antibody, peptide, and other biologics discovery across multiple targets. To support this effort, we are integrating advanced machine learning (ML), generative and agentic artificial intelligence (AI), and data-driven modeling to accelerate discovery and optimization across modalities. The Research Scientist, AI/ML will help build reproducible computational frameworks that strengthen AI/ML-assisted design pipelines. The primary focus of this role is oligonucleotide therapeutics, with growing contributions to peptide, antibody and biologics programs.

Job Summary:

In this role, you will develop sequence-aware predictive models that prioritize oligonucleotide therapeutics by exon-skipping response, integrating sequence, thermodynamic, and pre-mRNA structural features, and extend these approaches across PMOs, gapmers, siRNA–PMO hybrids, and conjugate designs. You will also contribute to AI/ML-driven de novo design and multi-objective optimization of antibodies, peptides, and other biologics, including modeling of protein structure and antibody–antigen interactions.

Working closely with chemists, biologists, and data scientists, you will benchmark and prospectively validate model predictions, helping turn computational insights into experimentally tested designs and expanding the client’s cross-modality design and decision-support capabilities.

Key Responsibilities:

• Develop and extend sequence-aware machine learning models that prioritize ASO designs by predicted exon-skipping response across multiple targets and modalities, including phosphorodiamidate morpholino oligomers (PMOs), gapmers, siRNA–PMO hybrids, and conjugate designs.
• Curate and harmonize internal datasets and external datasets drawn from the literature. Define robust sequence and structure features, such as thermodynamics, target accessibility, sequence motifs, and secondary structure, that drive model performance.
• Support the development and application of AI/ML methods for de novo design and multi-objective optimization of antibodies and other biologics.
• Contribute to modeling of protein structure, peptide, and antibody–antigen interactions.
• Build a reproducible computational framework covering data ingestion, feature engineering, model training, validation, and deployment across oligonucleotide and biologics programs.
• Establish benchmarks and prospective tests to assess model accuracy, robustness, and scalability, and partner with experimental teams to validate predictions.
• Evaluate and adopt proprietary and open-source tools to enhance modeling workflows and accelerate decision support.
• Maintain a clean, well-documented codebase and provide user guidance for cross-functional teams.
• Perform additional related tasks as assigned.

Required Skills & Education:

• PhD in Computational Biology, Computational Chemistry, Machine Learning, Bioengineering, Chemical Engineering, or a related field, with 1–2 years of relevant industry or postdoctoral experience
• Hands-on experience building deep learning, generative, or agentic AI models for nucleic acid and/or protein design
• Proficiency in Python and modern ML frameworks (e.g., PyTorch, JAX, TensorFlow, scikit-learn), with working knowledge of R and SQL
• Strong working knowledge of oligonucleotide design principles, such as hybridization thermodynamics, target accessibility, and RNA secondary structure
• Experience modeling exon-skipping efficiency or ASO/siRNA potency from sequence and pre-mRNA structural features
• Experience with protein and RNA language models (e.g., ESM, RNA-FM), structure prediction tools (e.g., AlphaFold, RoseTTAFold), and molecular modeling platforms (e.g., Schrödinger, MOE)
• Exposure to computational modeling of antibody–antigen sequence, structure, and binding interactions
• Familiarity with uncertainty quantification or active learning to guide experimental design
• Experience with reproducible development and deployment practices, including Git (GitHub/GitLab), Docker, database systems, and cloud computing (AWS preferred)
• Strong communication and collaboration skills across multidisciplinary teams of chemists, biologists, and data scientists, with a commitment to tackling challenges and continuous learning