Machine Learning Scientist — Agentic data pipelines

What this role involves

This role involves designing and building agentic systems for automated data acquisition, cleaning, and quality control for large-scale biomedical datasets used to train a multimodal transformer model. The ideal candidate has strong Python skills, experience with LLM APIs and agentic patterns, and familiarity with biomedical data formats. Remote work is available in the US or UK.

Skills this posting asks for

• python
• llm apis
• claude
• gpt
• agentic patterns
• tool use
• orchestration
• multi-step reasoning
• biomedical data
• pdb
• uniprot
• chembl
• sdf
• mol
• fasta
• data engineering
• etl
• data validation
• agent orchestration frameworks
• aws
• docker
• kubernetes
• multimodal biomedical data
• dataset construction

Requirements

• Level: mid
• Remote policy: remote

From the employer’s posting

Job Summary We are seeking a scientist to join our team at Iambic Therapeutics, working on data acquisition and curation for Enchant https://www.iambic.ai/post/enchant, our multimodal transformer model trained at scale on a wide variety of biomedical data. In this role, you will design and build a…