About Cartography Biosciences

Cartography Biosciences is a therapeutics organization creating the first atlas to identify targets that are specific enough to only engage cancerous cells, broad enough to work across cancer cells and patients, and safe enough to sidestep toxic side effects. Founded by Kevin Parker, Howard Chang, and Ansu Satpathy, Cartography is bridging immunology and computation to understand the critical differences between normal and cancerous cells, ultimately solving the challenge of finding the safest, most selective targets for a variety of immunotherapeutic approaches.

We are looking for a Scientist or Senior Scientist in computational antibody engineering to support efforts spanning from structure-based epitope analysis for target prioritization to design and optimization of next-generation multispecific T-cell engaging immunotherapies. You will build and apply computational pipelines across these areas, working closely with computational and antibody engineering teams to translate computational predictions into validated therapeutic candidates.

This role combines structural biology, computational modeling, and therapeutic antibody design. You will create new methods and pipelines to assess epitope positioning, accessibility, and cross-species conservation, and design corresponding multispecific antibody formats to identify molecules that meet the strict geometric and immunological requirements underlying best-in-class, highly selective multispecific T-cell engaging antibodies.

Key Responsibilities

• Develop and maintain computational pipelines for multispecific TCE target prioritization, including structural analysis of experimental and predicted protein structures, epitope accessibility and spatial positioning evaluation, and antibody-antigen binding geometry modeling.
• Collaborate with computational biology and antibody discovery teams to prioritize targets, define epitope specifications, and inform multispecific antibody target construct designs
• Evaluate, implement, and build pipelines around emerging de novo protein binder design tools to generate and nominate novel therapeutic antibody and VHH candidates for experimental validation.
• Build and apply computational antibody lead optimization workflows to improve pharmacological activity and developability properties (biophysical stability, chemical stability, aggregation propensity), leveraging experimental data to drive iterative design-build-test cycles that advance candidates toward clinical development.
• Coordinate with protein sciences, pharmacology, and analytics colleagues for production, testing, and characterization of computationally designed antibodies.
• Articulate and present complex computational engineering concepts to diverse audiences, including internal scientific teams and external investors.

Required Qualifications

• Scientist: PhD in Structural Biology, Protein Design, Biophysics, Biochemistry, or other related field.
• Senior Scientist: PhD plus at least 2 years of relevant industry or postdoctoral experience.
• Deep knowledge of protein structure analysis, visualization, and interpretation using tools like PyMOL, ChimeraX, or similar.
• Strong understanding of antibody-antigen interactions, epitope mapping, and binding interfaces.
• Knowledge of membrane protein structure, topology, and cell architecture.
• Experience with computational structural biology tools, including homology modeling, structure prediction, and docking.
• Proficiency in Python for scripting and data analysis.
• Comfortable working in Unix or Linux terminal environments.
• Ability to build automated pipelines by integrating existing computational tools.

Preferred Qualifications

• Experience with protein structure prediction tools (AlphaFold, Boltz, OpenFold) or generative protein design tools (RFdiffusion, BoltzGen, BindCraft).
• Familiarity with T-cell engaging antibody platforms like BiTEs, TCEs, and bispecifics.
• Experience with antibody characterization or lead optimization, including assessment and engineering of developability properties (stability, aggregation, immunogenicity, etc.).
• Knowledge of homology and epitope prediction algorithms and tools.
• Hands-on laboratory experience in molecular biology, protein expression/purification, or biophysical and structural characterization (e.g., SPR, BLI, DSF, EM, Crystalography).
• Experience with cloud computing platforms, preferably GCP.
• Background in cancer biology or immunology.
• Proven track record of target identification or therapeutic antibody development.