Staff Scientist - Modeling Tumor Evolution and Treatment (Hybrid)

City of Hope•Duarte, CA

6d•Hybrid

About The Position

Join the forefront of groundbreaking research at City of Hope where we're changing lives and making a real difference in the fight against cancer, diabetes, and other life-threatening illnesses. Our dedicated and compassionate faculty and staff are driven by a common mission: Contribute to innovative approaches in predicting, preventing, and curing diseases, shaping the future of medicine through cutting-edge research. The Bild Laboratory at City of Hope uses systems biology to understand how tumors evolve under therapy, uncover resistance mechanisms, and identify actionable vulnerabilities. We integrate longitudinal patient cohorts with single-cell and bulk multi-omics, liquid biopsy, and patient-derived models, partnering closely with clinicians at an NCI-designated Comprehensive Cancer Center. We are seeking a Staff Scientist to lead computational projects at the interface of tumor evolution, liquid biopsy, and machine learning. The successful candidate will develop and apply methods that integrate multimodal molecular and clinical data (genomic, epigenomic, transcriptomic) across serial patient timepoints to model tumor population dynamics during treatment and predict clinical outcomes. This is a highly collaborative, translational role for a scientist who wants to connect methods development with impactful questions in cancer biology. Learn more about Dr. Bild’s lab here.

Requirements

A PhD (or equivalent) in computational biology, bioinformatics, systems biology, biomedical engineering, statistics, computer science, or a closely related quantitative field.
Demonstrated expertise across most of the following areas: Cancer biology domain knowledge
Working understanding of tumor evolution and clonal dynamics, pathway and signaling biology in the context of the hallmarks of cancer, and the molecular biology connecting DNA mutation and methylation to RNA and protein function.
Computational and machine learning skills
Proficiency in large-scale genomic data management and bioinformatic processing, including fluency with R/Bioconductor workflows and Python scientific stacks.
Hands-on experience with deep learning frameworks such as PyTorch or TensorFlow, and ideally with probabilistic programming tools such as Pyro or Stan.
Experience with multimodal data fusion and building efficient, scalable data pipelines for large genomic datasets.
Statistics and mathematics
Strong grounding in multivariate statistics, dimensionality reduction, and latent variable modeling.
Experience with temporal or dynamical modeling, Bayesian inference, and survival analysis for clinical outcome data.
Scholarly record and collaboration
A track record of first-author peer-reviewed publications (or preprints) appropriate to career stage, and the communication skills to work effectively across a team that spans multiple disciplines.

Nice To Haves

Familiarity with liquid biopsy modalities (ctDNA, cfDNA methylation, CTCs) and their clinical applications, along with awareness of oncology biomarker validation frameworks, is strongly preferred.

Responsibilities

Build probabilistic models of tumor dynamics from serial ctDNA and tissue samples.
Develop deep learning frameworks that integrate multimodal data to predict therapeutic response.
Construct scalable pipelines for analyzing large longitudinal genomic cohorts.
Validate computationally derived biomarkers in collaboration with experimental and clinical teams.
Publish in high-impact journals and present at major conferences.
Mentor junior lab members.
Develop an independent research direction that positions you for a faculty or senior industry role.