Biology Data Quality Engineer(m/w/x)

Description

You will ensure the integrity of complex biological datasets by building automated validation pipelines and standardizing data, playing a vital role in training foundation models.

Requirements

• •Team-first attitude and independence
• •Curiosity and detail-orientation
• •Ability to thrive in dynamic environments
• •Strong domain expertise in biology
• •Strong computational and hands-on skills
• •Deep understanding of transcriptomics data
• •Knowledge of genomics and proteomics data
• •Experience in data quality control
• •Familiarity with data validation tools
• •Strong analytical and problem-solving skills
• •Proficiency in Python
• •Knowledge of data visualization libraries
• •Excellent written and verbal communication
• •MSc in Biology, Computational Biology, or Bioinformatics
• •Experience in machine learning for histology
• •Experience working with AWS
• •Experience with data annotation guidelines
• •Experience with data ontologies
• •Experience building large-scale data collections
• •Experience in spatial alignment of datasets

Tasks

• •Develop comprehensive data validation protocols for histology, omics, and clinical datasets
• •Design automated pipelines to streamline data validation and identify issues early
• •Establish data standardization practices for seamless integration across different data types
• •Curate biological datasets to enhance their usability for machine learning
• •Collaborate with the R&D team to address specific data quality requirements
• •Communicate findings and recommendations to technical and non-technical stakeholders
• •Coordinate and synchronize data standards with external providers
• •Document quality assessment procedures, validation results, and data specifications
• •Generate regular reports on data quality metrics and trends
• •Evaluate external public data sources for foundation model training suitability
• •Implement improvements to data quality processes based on industry best practices

Tools & Technologies

Benefits