BioAI Data Scientist - Lab Data Quality & Pipelines

Userc Dehradun; Lausanne; On-site; CHF 110,000 - 150,000; Full time

Job summary

Adaptyv Lausanne is hiring a Data Scientist for Lab & Protein Data, on-site in Lausanne. You will build the data science layer of the foundry to convert messy experimental readouts into clean, structured data used by customers and AI models.

You will work closely with lab scientists, software engineers, and ML teams. The role requires Python expertise, strong bioinformatics grounding, and experience turning real-world experimental data into reliable datasets.

Qualifications

• Strong data science / bioinformatics background.
• Fluent in Python with Pandas and NumPy.
• Experience handling real-world experimental data end to end.

Responsibilities

• Own the scientific logic of data quality across the foundry: define what good data looks like for each assay type and implement automated checks.
• Build anomaly detection and QC models to catch data quality issues, distinguishing signal from noise.
• Collaborate with software and ML teams to specify, review, and improve automated data pipelines and data routing rules.
• Link experimental results to protein sequence, structure and design to reinforce insights between wet-lab data and computational models.
• Turn foundry outputs into structured, documented, benchmark-grade datasets for customers and model training/evaluation.
• Apply rigorous statistics to multi-condition data across thousands of samples for interpretable, comparable results.

Skills

Python

Bioinformatics

Pandas

NumPy

Tools

Pandas

NumPy

Job description

Adaptyv Lausanne is hiring a Data Scientist for Lab & Protein Data, on-site in Lausanne. You will build the data science layer of the foundry to convert messy experimental readouts into clean, structured data used by customers and AI models.

You will work closely with lab scientists, software engineers, and ML teams. The role requires Python expertise, strong bioinformatics grounding, and experience turning real-world experimental data into reliable datasets.