Principal Scientist - Protein MIL

Job Description

Position located in Boston, MA

\n

\n

Responsibilities:

\n

\n

\n
• Lead computational biology and machine learning efforts supporting protein discovery, engineering, and characterization.

\n

• Develop, fine-tune, and benchmark deep learning and foundation models for protein structure prediction, protein design, and antibody/binder discovery.

\n

• Build predictive models for protein properties including stability, aggregation, expression, binding affinity, and developability.

\n

• Design and execute computational protein and antibody design campaigns and integrate results with experimental validation cycles.

\n

• Develop scalable computational pipelines for antibody discovery, protein characterization, sequencing, proteomics, and other biological datasets.

\n

• Build data platforms, databases, APIs, and visualization tools that enable researchers to efficiently access and utilize complex biological data.

\n

• Collaborate with experimental scientists to design studies, analyze results, and integrate computational approaches into laboratory workflows.

\n

• Manage cloud, GPU, and high-performance computing environments supporting machine learning and large-scale biological analysis.

\n

• Lead, mentor, and develop a small team of computational biologists and bioinformaticians.

\n

• Establish best practices for data management, reproducibility, version control, model deployment, and MLOps.

\n

• Communicate computational strategies and findings to both technical and non-technical audiences and contribute to publications, intellectual property, and product development.

\n

\n

\n

Requirements:

\n

\n

\n
• PhD in computational biology, bioinformatics, biophysics, machine learning, or a related field, with strong experience in protein science or biochemistry.

\n

• 5+ years of relevant industry or research experience, including technical leadership or experience mentoring/managing computational scientists.

\n

• Strong Python programming skills and hands-on experience with deep learning frameworks such as PyTorch.

\n

• Demonstrated experience developing, modifying, training, or applying machine learning models for protein structure prediction and/or protein design.

\n

• Experience working with multimodal biological datasets, including sequence, structure, assay, sequencing, or proteomics data.

\n

• Proven experience with de novo protein, binder, or antibody design and experimental validation.

\n

• Strong understanding of computational protein science and the ability to translate research methods into practical tools and workflows.

\n