AI in Residence, Computational Protein Design
Xairatherapeutics · Seattle, Washington, United States
About this role
**About Xaira Therapeutics** Xaira is an innovative biotech startup leveraging AI to transform drug discovery and development. The company is building generative AI models to design protein and antibody therapeutics, including foundation models for biology and disease to improve target elucidation and patient stratification. Xaira is headquartered in the San Francisco Bay Area, Seattle, and London. **AI in Residence** AI in Residence is a highly selective role at the intersection of frontier machine learning and drug discovery. Designed as an industry alternative to a traditional postdoctoral position, the program is for exceptional researchers and engineers who want to apply advanced AI to real biomedical problems end to end—from data to deployed systems. Residents join a small cohort working on high-impact AI efforts across Xaira. You’ll collaborate closely with AI scientists, research engineers, and drug discovery teams to design, build, and ship machine learning capabilities that directly influence therapeutic programs. **What You’ll Do** - Develop and advance ML models for protein and antibody design using biophysical data, affinity data, library display data, protein structure datasets, and protein sequence datasets - Design and implement scalable pipelines for data curation, training, evaluation, and inference integrated into discovery workflows - Own projects end-to-end: problem framing → prototyping → validation → deployment - Evaluate robustness and reliability (generalization, uncertainty, failure modes), plus interpretability where it supports scientific decision-making - Contribute technical leadership by proposing new directions, shaping platform capabilities, and raising engineering/research standards through collaboration **You Might Work On (Examples)** - Foundation / representation models for protein/antibody structure, sequence, and property modeling/prediction - Methods for small, biased, noisy datasets; distribution shift; and uncertainty estimation - ML systems for experimental prioritization, assay interpretation, or translational signal discovery You may also work on evaluation frameworks and benchmarks tailored to discovery decision-making, and tooling that makes models usable by scientists (interfaces, automation, monitoring). **What Success Looks Like** - You ship one or more models or pipelines used in real discovery workflows - Your work improves decision quality (e.g., better prioritization, faster iteration, clearer uncertainty) - You raise the bar on evaluation rigor and reproducibility (strong baselines, error analysis, reliable metrics) - You leave behind maintainable systems (tests, documentation, monitoring) that others can build on **We Value** - Strong research judgment (choosing the right problems and knowing what “good evidence” looks like) - Rigor (careful experimental design, ablations, error analysis, honest reporting) - Systems thinking (reliability, scalability, maintainability—not just prototypes) - Clear communication (writing, documentation, sharing decisions/assumptions) - Collaborative execution with scientific and engineering partners **Program Structure** - **Duration:** 6–12 months - **Start Dates:** First hires beginning August 2026, with rolling applications and additional intakes in Fall 2026 - **Cohort Size:** Small, highly selective cohort to enable meaningful ownership and close collaboration - **Mentorship & Support:** Dedicated technical mentor, plus structured feedbac
Listing freshness
CronJobs last confirmed this listing 21h ago. If its source stops confirming the opening for seven days, this page is removed from active inventory.