Senior/Staff Machine Learning Scientist, Computational Pathology

Artera is an artificial intelligence company dedicated to transforming cancer care. It develops foundation models that analyze clinical and pathology data to guide therapy selection and improve outcomes for cancer patients. The role involves designing, directing, and evaluating autonomous research agents for ML development, answering specific scientific questions, and owning an AI biomarker end to end, including validation, regulatory submission, and production. The senior or staff scientist sets technical direction for scientists and engineers, works on model generalization across scanners, stains, and sites, and builds next-generation pathology foundation models. At the Staff level, the role also sets direction across programs and helps shape the AI roadmap with leadership. A PhD is not required; prior regulatory experience is a strong plus.

Responsibilities

Own AI biomarker end to end, from problem framing with product, medical, and biostatistics partners through validation, regulatory submission, and production; Lead the next generation of pan-cancer self-supervised pathology foundation models and downstream models (multiple-instance learning, time-to-event, segmentation), with generalization as a first-order objective; Own the reproducibility and robustness of model predictions across scanners, institutions, staining protocols, and patient populations; Manage coding agents to propose and execute experiments, improve tooling efficiency, and identify biological insights explaining model behavior; Serve as technical lead: set technical strategy, break multi-quarter programs into milestones, manage dependencies, surface risks early, and hold submission and launch dates; Present findings to product, medical, and biostatistics teams, author and defend regulatory and quality documentation, and represent AI in design and development reviews; Mentor ML scientists and engineers and raise the bar on scientific rigor, code quality, and written communication; Publish in peer-reviewed journals, present at clinical and ML venues, and support external academic and industry collaborations

Requirements

5+ years of industry experience building deep learning systems (PyTorch); Hands-on experience with coding agents like Cursor or Claude Code; Track record of taking models beyond a notebook, including launching and monitoring ML products in production and evaluating them rigorously on messy, real-world data; 2+ years as a technical lead for complex ML programs (scoping problems, setting technical direction, sequencing work, managing dependencies and risk across teams on dated deliverables); Demonstrated depth in oncology or biomarker development (cancer biology and treatment pathways, clinical endpoints, risk stratification, what makes a biomarker clinically actionable); Proven ability to communicate complex ML concepts to cross-functional, non-ML collaborators; Experience mentoring or managing ML scientists and engineers

Nice to have

ML on complex clinical data (medical imaging, multi-omics, longitudinal records); Weakly supervised learning (e.g., MIL) and survival analysis; Self-supervised representation learning (e.g., DINOv3) and adapting medical foundation models to clinical tasks; ML in regulated environments (FDA 510(k)/De Novo, SaMD, design controls, CLIA/LDT); Cloud-scale training and orchestration (e.g., Flyte/Union, AWS)