Principal Scientist – Biomedical Machine Learning

• Build, fine-tune, and benchmark Machine Learning and Deep Learning models on biomedical data, with an initial focus on adapting pathology foundation models (e.g., Prov-GigaPath, Virchow, and H-Optimus-0) as well as multimodal imaging and omics models for downstream predictive tasks.
• Collaborate closely with computational biologists, oncologists, and pathologists to translate complex biological questions into well-defined machine learning problems and convert model outputs into biologically and clinically meaningful insights.
• Embed rigorous evaluation, validation, and interpretability throughout the model development lifecycle, leveraging approaches such as attention- and gradient-based methods, explainability techniques, and counterfactual analyses.
• Develop reusable and well-documented modeling frameworks, components, and best practices that accelerate future projects and promote scalability across the organization.
• Stay at the forefront of advances in computational pathology, multimodal AI, and machine learning, identifying and applying the most relevant innovations to deliver scientific impact.

Requirements

• PhD in Computer Science, Data Science, Bioinformatics, Computational Biology, or another relevant scientific discipline, combined with hands-on industry experience in Machine Learning and Deep Learning at a senior level.
• Deep and demonstrable expertise in Machine Learning and Deep Learning, supported by strong proficiency in Python and modern deep learning frameworks (e.g., PyTorch), as well as proven experience in fine-tuning, transfer learning, and adapting large pre-trained models.
• Strong hands-on experience working with biological and biomedical data, such as transcriptomics/RNA-seq, digital pathology, medical imaging, or other omics data, including a solid understanding of domain-specific challenges such as normalization, batch effects, label generation, and data quality considerations.
• Strong scientific rigor and critical thinking skills, with the ability to assess whether models are learning meaningful biological signals and to design robust evaluation strategies that withstand biological and clinical scrutiny.
• Proven experience leading ML projects end-to-end, collaborating effectively with both technical and domain experts, and applying software engineering best practices, including version control, reproducibility, and development on modern cloud-based ML platforms.

Core Competencies

Demonstrates expertise in Machine Learning and Deep Learning, particularly in the context of biomedical data, with a strong focus on model evaluation, interpretability, and collaboration with domain experts. Proficient in developing scalable modeling frameworks and applying advanced techniques to derive clinically meaningful insights.

Highest-signal resume keywords

• PhD In Computer Science
• Machine Learning Expertise
• Deep Learning Expertise
• Python Proficiency
• Experience With Biomedical Data

ATS Optimization Keywords

Hard Skills

• Machine Learning
• Deep Learning
• Fine-Tuning
• Transfer Learning
• Model Evaluation
• Data Normalization
• Batch Effects
• Label Generation
• Data Quality Assessment
• Scientific Rigor

Soft Skills

• Critical Thinking
• Collaboration
• Communication

Industry Keywords

• Computational Biology
• Biomedical Data
• Digital Pathology
• Medical Imaging
• Transcriptomics
• Omics Data
• Computational Pathology
• Multimodal AI

Tools & Technologies

• PyTorch
• Cloud-Based ML Platforms
• Version Control