Associate Director of Computational Biology & Bioinformatics

Institute for Protein Innovation•Boston, MA

3d•Onsite

About The Position

The Associate Director of Computational Biology & Bioinformatics will help lead IPI's computational protein science team and be responsible for the machine learning and data systems that support work across the Institute. This includes the following functional teams: antibody and antigen discovery, protein characterization, neuroscience, lab automation and lab operations. This role is responsible for training and applying foundation models for protein structure prediction and design, building models that predict biophysical properties from sequence and structure and turning large multimodal biological datasets into tools and portals that can be effectively utilized across the Institute. This position provides a combination of hands-on technical work with team leadership skills to fulfill responsibilities and achieve goals. The position will collaborate closely with the Associate Director & Program Manager of the Antibody Platform and reports to the Senior Director of the Antibody Platform.

Requirements

PhD in computational biology, bioinformatics, biophysics, machine learning, or a related field, with a strong background in protein science or biochemistry.
5 or more years of relevant experience, including experience leading or mentoring computational staff or serving as a technical lead.
Strong Python and hands-on experience with deep learning frameworks such as PyTorch.
Experience developing, modifying, and applying protein machine learning models for structure prediction and design.
Experience building or training models on multimodal biological data, with a track record shown through publications, patents, or products.
Experience with de novo protein and antibody design and validation cycles.

Nice To Haves

Direct experience managing a team of two to four people is a plus.
Experience with next generation sequencing analysis.
Experience building data portals, APIs, or databases for large biological datasets.
Experience with cloud computing and high-performance computing or GPU environments.
Familiarity with antibody discovery, proteomics, or protein biophysical characterization assays.
Experience integrating computational predictions with wet-lab workflows, including LIMS or ELN systems.

Responsibilities

Train, fine-tune, and benchmark foundation models for protein folding and design, including structure prediction models and generative models for de novo binder and antibody design, and integrate these models for routine use in antigen and antibody discovery projects.
Build and validate models that predict biophysical properties such as stability, aggregation, expression, binding affinity, and developability, using multimodal data across sequence, structure, next generation sequencing, proteomics, and assay results.
Run in silico binder and antibody design campaigns and pair them with experimental rounds so predictions are tested and the results feed back into the models.
Develop pipelines and platforms for in vitro antibody discovery data, protein biophysical characterization, proteomics, and next generation sequencing analysis.
Build and maintain web portals and databases for large biological datasets, including IPI's external antigen and antibody catalogs (for example OpenAntigens) and internal research databases.
Work with teams and groups across the Institute to design experiments, interpret and analyze results, and effectively integrate computational tools into established team workflows.
Manage cloud and high-performance computing environments, including GPU infrastructure for model training and large-scale analysis.
Lead and mentor a small team of computational biologists and bioinformaticians.
Effectively present computational analyses to technical and non-technical audiences and contribute to publications, patents, and products.
Establish standards for data management, version control, reproducibility, and MLOps in the group.