Software Engineer — Agentic data pipelines

Summary

Design and build agentic systems that automatically acquire, clean, format, and quality-control large-scale biomedical datasets for training the Enchant multimodal transformer model. You will develop LLM-based agents that generate trustworthy pipeline code, implement automated QC workflows, and maintain distributed data pipelines in production. The role requires strong Python engineering, hands-on experience with LLM APIs and agent patterns, familiarity with biomedical data formats, and data engineering fundamentals including ETL design and validation at scale.