Machine Learning Scientist/Sr. Scientist - Drug Target Discovery

• Drug Target Discovery: Develop and apply ML/AI methods to identify and prioritize novel drug targets, including T cell engagers, ADCs, and multispecific antibodies.
• Therapeutic Design: Engineer and optimize therapeutic strategies using ML models, including payload strategies and checkpoint combinations for cancer indications.
• Model Development: Build scalable and interpretable machine learning models (e.g., DL, VAEs, GNNs) using public and internal multi-omics, structural, and clinical datasets.
• Data Mining for Oncology: Analyze complex datasets (RNA-seq, proteomics, perturbation, clinical trial data) to generate actionable insights into cancer biology and treatment response.
• Cross-functional Collaboration: Work closely with protein engineers, immunologists, and translational scientists to integrate AI-driven hypotheses into the drug pipeline.
• Scientific Feedback Loop: Interpret outputs from ML models and guide experimental validation, providing insight into feasibility, mechanistic pathways, and therapeutic relevanc

• PhD or Master’s in Computer Science, Machine Learning, Computational Biology, Bioinformatics, Biostatistics, or a related field.
• 5+ years of industry experience in drug discovery or therapeutic development required.
• Strong experience with drug development platforms, ideally including target selection/validation and biologic modality development (ADC, TCE, antibodies).
• Demonstrated application of ML/AI to therapeutic R&D (e.g., gene expression modeling, target nomination, protein interaction prediction).
• Familiarity with oncology-focused discovery, especially involving immune checkpoints, payload strategies, or tumor-specific targets.
• Hands-on proficiency with Python, R, PyTorch or TensorFlow, and related bioinformatics/ML tools.
• Exposure to protein structure modeling or antibody engineering is highly desirable.
• Experience with multi-modal data integration, including single-cell, bulk RNA-seq, proteomics, or clinical data.

Preferred Experience

• Prior work on T cell engagers, ADC programs, or bispecific antibodies.
• Understanding of protein-ligand interactions, payload selection, or immune checkpoint design.
• Knowledge of tools such as AlphaFold, Rosetta, DiffDock, or protein language models.
• Experience working with drug development platforms across cancer and other disease areas.

This role is not a fit for:

• Generalist data scientists or clinical data managers without direct therapeutic development experience.
• Candidates lacking domain exposure to biologics, oncology, or drug platform work.

What We Offer

• The opportunity to directly impact first-in-class cancer immunotherapies.
• A collaborative and fast-moving environment bridging biology, engineering, and AI.
• Access to internal pipelines, multi-omics data, and wet-lab teams for experimental feedback.
• Competitive salary, stock options, and onsite culture in Redmond, WA.

Powered by JazzHR