Data Scientist, Lab & Protein Data

About the role

Adaptyv is building an automated lab that lets AI agents run biology experiments. As a Data Scientist you will turn large volumes of raw, messy experimental readouts into clean, trustworthy, structured data for customers, models, and internal scientists.

Key responsibilities

• Define and implement scientific logic for data quality across multiple assay types, creating automated checks for signal ranges, control thresholds, and failure modes.
• Build anomaly detection and quality‑control models to identify assay drift, instrument variability, plate effects, and false passes/fails.
• Collaborate with software and ML teams to improve automated data pipelines, specifying requirements for flagging, auto‑rejecting, or routing data for human review.
• Link experimental results back to protein sequence, structure, and design, ensuring wet‑lab data and computational models reinforce each other.
• Produce benchmark‑grade, documented datasets for customers and for training protein‑design models.

Required profile

• Strong data‑science or bioinformatics background with hands‑on experience handling messy experimental data end‑to‑end.
• Solid understanding of proteins, assays, and sequence‑structure‑function relationships.
• Statistical maturity in process control, anomaly detection, and handling batch effects.
• Proven track record of shipping production‑ready pipelines, tools, models, or datasets.
• Comfort working across lab, software, and ML teams and treating automation as core responsibility.

Required skills

• Python (including pandas, numpy, and the scientific stack).