Data Scientist, Lab & Protein Data

The role

You will build the data science layer of the foundry to turn raw experimental readouts into structured data. You will own scientific logic for data quality, build anomaly detection models, and connect experimental results to protein design.

What you will do

• Own the scientific logic of data quality across the foundry
• Build anomaly detection and QC models to catch bad data
• Work with software and ML teams to improve automated data pipelines
• Connect experimental results back to the protein side
• Turn foundry output into structured, benchmark-grade datasets
• Apply statistical rigor to multi-condition data at scale

Required qualifications

• Strong data science / bioinformatics background
• Fluent in Python (pandas, numpy, the scientific stack)
• Comfortable owning messy, real-world experimental data end to end
• Genuine biology grounding in proteins, assays, and sequence/structure/function
• Statistical maturity in process control, anomaly detection, and handling variability
• Prolific builder with experience shipping pipelines, tools, models, or datasets
• AI-native builder using coding agents like Claude Code
• Interdisciplinary instinct to work across lab bench, software, and ML

Nice to have

• experience with protein/sequence-structure data (bioinformatics tooling, structural data)
• ML on experimental data
• building datasets for model training and benchmarking

About the company

Adaptyv is building an automated lab that lets AI agents run biology experiments. They are a fast growing biotech company building infrastructure that gives AI agents access to the physical world.