Contract Research Scientist, Computational Biology & AI/ML

Commonwealth Sciences, Inc.; Boston (MA); On-site; USD 140,000 - 190,000; Full time

Job summary

Commonwealth Sciences, Inc. in Boston is seeking a PhD-level scientist to develop ML and modeling approaches for accelerating therapeutic discovery across oligonucleotide and antibody platforms.

You will build predictive and generative models, integrate diverse datasets, and work closely with lab scientists to validate predictions and drive data-driven strategies.

Qualifications

• PhD in a quantitative field with 3+ years of industry experience.
• Experience applying computational methods to protein/antibody design.
• Strong programming in Python; experience with R/SQL is a plus.
• Proficiency with ML frameworks such as PyTorch, TensorFlow, and scikit-learn.

Responsibilities

• Develop and apply machine learning and computational modeling approaches to accelerate therapeutic discovery across oligonucleotide and biologic platforms.
• Build predictive and generative models to support antibody engineering, including antibody–antigen interaction modeling and sequence analysis.
• Apply AI/ML techniques to identify and rank promising ASO candidates based on sequence characteristics and other parameters.
• Develop scalable, reproducible workflows spanning data preparation, feature generation, model development, training, evaluation and implementation.

Skills

Deep learning

Antibody design

Protein modeling

Python

Generative models

Data integration

Education

PhD in Computational Biology

PhD in Computational Chemistry

PhD in Biomedical Engineering

Tools

PyTorch

TensorFlow

scikit-learn

JAX

Job description

• Develop and apply machine learning and computational modeling approaches to accelerate therapeutic discovery across oligonucleotide and biologic platforms.
• Build predictive and generative models to support antibody engineering, including antibody–antigen interaction modeling, sequence analysis, structural prediction, and de novo protein design.
• Apply AI/ML techniques to identify and rank promising ASO candidates based on sequence characteristics, target accessibility, exon-skipping activity, and other relevant biological parameters.
• Develop computational strategies for optimizing antibodies, antigens, ADCs, oligonucleotides, and other emerging therapeutic modalities against multiple design objectives.
• Create scalable, reproducible workflows spanning data preparation, feature generation, model development, training, evaluation, and implementation.
• Integrate sequence, structural, biochemical, and experimental datasets from internal programs, published literature, and external sources to improve model performance and biological insight.
• Investigate and incorporate relevant molecular descriptors, including sequence motifs, thermodynamic properties, structural accessibility, secondary structure, binding characteristics, and other predictive features.
• Establish rigorous model evaluation, benchmarking, and validation strategies and work closely with laboratory scientists to test computational predictions experimentally.
• Assess emerging AI/ML methodologies, commercial platforms, open-source packages, and protein/oligonucleotide modeling technologies for potential integration into discovery workflows.
• Develop well-structured, maintainable code and computational documentation that enables scientists across multidisciplinary teams to effectively use and interpret modeling tools.
• Communicate computational findings, model performance, and design recommendations to scientists and project teams and contribute to data-driven therapeutic development strategies.

Requirements:

• PhD in Computational Biology, Computational Chemistry, Machine Learning, Bioengineering, Chemical Engineering, Biomedical Engineering, or a closely related quantitative discipline, with at least 3 years of relevant industry experience.
• Demonstrated experience applying computational methods to protein, antibody, DNA, RNA, or oligonucleotide design, preferably within a drug discovery or biotechnology environment.
• Strong understanding of antibody engineering and computational approaches for analyzing antibody–antigen sequence, structure, binding, and interaction properties.
• Experience developing or applying advanced machine learning methodologies, including deep neural networks, transformers, graph-based models, protein language models, generative models, or related approaches.
• Hands‑on experience using AI/ML to solve biological or molecular design problems, including predictive modeling, sequence analysis, structure prediction, or optimization.
• Knowledge of oligonucleotide therapeutics, ASOs, RNA biology, exon skipping, siRNA, PMO/gapmer chemistry, or related modalities is highly desirable.
• Strong programming capabilities in Python, with experience in one or more additional languages such as R or SQL.
• Proficiency with modern machine learning and scientific computing frameworks such as PyTorch, TensorFlow, scikit‑learn, JAX, or comparable technologies.
• Experience working with large biological datasets and integrating sequence, structural, experimental, and literature-derived information for computational modeling.