Software Engineer for Data Pipelines

Job Summary

Combining software engineering expertise with a scientific understanding of biomedical data, the full-time remote Software Engineer for Data Pipelines will design and build agentic systems for data acquisition and curation, focusing on developing AI agents to manage large-scale biomedical datasets.

Key responsibilities

• Design, build, and maintain agentic systems that convert biomedical data sources into reviewed, versioned datasets
• Implement automated quality-control workflows to detect anomalies and enforce data standards
• Collaborate with ML scientists to translate data requirements into scalable acquisition and processing systems

Required qualifications

• Master's degree in a computational STEM field, or a Bachelor's with 2+ years of industry experience
• Strong Python engineering skills with experience in production-quality software development
• Hands-on experience with LLM APIs and agentic patterns such as tool use and orchestration
• Familiarity with biomedical or chemical data sources and formats
• Comfort with data engineering fundamentals, including ETL design and data validation