Research Scientist, Life Sciences (Large Molecules, Antibody Design)

Anthropic's Life Sciences team is building a research group focused on biological discoveries by combining AI with hands-on biological research. We're seeking a research scientist with deep expertise in therapeutic antibodies to join the team. Our goal is to speed up progress in the life sciences by an order of magnitude, and this role puts that mission into practice. You'll be an expert in antibody design and engineering who has taken antibodies through the whole process, from target selection and lead optimization to candidate selection and IND-enabling studies. Above all, you'll close the loop between AI-generated hypotheses and experimental data to share with the community. Working alongside AI researchers and engineers, you'll drive antibody programs end to end and pressure-test AI-designed antibodies against the bar a real drug candidate has to clear.

This role is fully on-site in the San Francisco Bay Area.

Key responsibilities

• Design and engineer therapeutic antibodies and oversee programs end to end, including target and epitope selection, choice of format (IgG, Fab, scFv, VHH, bispecific), humanization, affinity maturation, Fc engineering, and candidate selection
• Define the screening cascade for each program, from binding kinetics (SPR, BLI), epitope binning, and species cross-reactivity to cell-based functional assays and developability (expression, aggregation, polyreactivity, stability, viscosity, immunogenicity risk)
• Plan the path from lead to IND-enabling studies, including in vivo pharmacology, pharmacokinetics, toxicology, and the handoff to process development and manufacturing
• Coordinate antibody production, characterization, and in vitro and in vivo studies with external contract research organizations and academic partners
• Evaluate AI-designed antibodies, drive them to experimental readout, and feed results back to research teams
• Ensure experimental data across programs is high quality and well documented, including sequences, protocols, raw data, and failure modes
• Communicate findings clearly to biology, AI research, and life sciences audiences

…