Biotech Data Scientist — AI-Driven Lab Data & Pipelines

Adaptyv; Vaud; On-site; CHF 120,000 - 180,000; Full time

Job summary

Adaptyv is building an automated lab where AI-driven agents design experiments and data pipelines transform raw measurements into clean, benchmark-grade datasets. This role focuses on the data quality and governance layer of the foundry, ensuring that data are accurate, comparable and ready for downstream AI model training.

This position partners with lab scientists, software engineers, and customers to define and implement automated QC, develop anomaly detection, and connect results back to

Qualifications

• Strong data science / bioinformatics background with Python (pandas, numpy).
• Genuine biology grounding with protein/sequence data understanding.
• Statistical maturity: process control, anomaly detection, batch effects.
• Prolific builder with end-to-end pipelines, datasets, and models.
• AI-native builder with experience using coding agents.
• Interdisciplinary by instinct across lab, software and ML.
• Bonus: experience with protein/sequence data or model training datasets.

Responsibilities

• Own the data quality logic across the foundry for each assay type and automate checks.
• Build anomaly detection and QC models to catch subtle data issues.
• Define data pipelines requirements with software/ML teams and guide data routing.
• Link experimental results to sequence, structure, and design to reinforce models.
• Turn foundry outputs into structured, benchmark-grade datasets for customers and model training.
• Apply statistics to multi-condition data at scale and ensure interpretability across runs.

Skills

Python (pandas, numpy)

Biology/data science background

Statistics / anomaly detection

Data quality mindset

AI-native builder

Education

MSc/PhD in bioinformatics / computational biology / data science

Tools

SQL

scikit-learn

TensorFlow/PyTorch

Pandas

Job description

Adaptyv is building an automated lab where AI-driven agents design experiments and data pipelines transform raw measurements into clean, benchmark-grade datasets. This role focuses on the data quality and governance layer of the foundry, ensuring that data are accurate, comparable and ready for downstream AI model training.

This position partners with lab scientists, software engineers, and customers to define and implement automated QC, develop anomaly detection, and connect results back to