Adaptyv seeks a Data Scientist to build the data science layer for its automated lab, transforming raw experimental data into structured, high-quality datasets for protein design and AI training.
This position focuses on developing the data science infrastructure for Adaptyv's automated laboratory. The role involves converting raw experimental outputs into reliable, structured data that supports the company's mission of enabling AI agents to design novel proteins and iterate on biological hypotheses.
Responsibilities
- Develop the data science framework for the automated lab to transform raw experimental outputs into clean, structured, and reliable datasets.
- Define data quality standards for various assay types and implement automated checks to ensure scientific integrity.
- Create anomaly detection and quality control models to identify subtle data issues and distinguish meaningful signals from statistical noise.
- Collaborate with software and machine learning teams to refine automated pipelines that process instrument data.
- Integrate experimental results with protein sequence, structure, and design data to align wet-lab findings with computational models.
- Generate benchmark-grade datasets from laboratory outputs to support customer needs and the training and evaluation of protein-design models.
- Apply rigorous statistical methods to analyze multi-condition data at scale, ensuring results are interpretable and comparable across different experimental runs.
Requirements
- Strong background in data science or bioinformatics with proficiency in Python, including pandas and numpy, and experience managing complex, real-world experimental data.
- Solid understanding of biology, particularly proteins, assays, and the relationship between sequence, structure, and function.
- Advanced statistical skills, including process control, anomaly detection, and handling variability and batch effects, with the ability to differentiate between data drift and noise.
- Proven track record of delivering end-to-end pipelines, tools, models, and datasets into production, rather than just developing prototypes.
- Experience using AI coding assistants like Claude Code and the ability to critically evaluate their outputs.
- Comfortable working across disciplines, bridging the gap between laboratory operations, software development, and machine learning.
Nice to have
- Experience working with protein sequence and structure data, bioinformatics tools, or structural data.
- Background in applying machine learning to experimental data or building datasets for model training and benchmarking.
About the company
Adaptyv is a rapidly growing biotech company trusted by leading biopharmaceutical firms, frontier AI labs, and techbio organizations. The company is pioneering agentic science by building an automated laboratory where AI agents can design novel proteins, propose hypotheses, and iterate on experimental results. The lab is supported by a comprehensive software and hardware stack that includes API-controllable devices, orchestrated systems, full observability, processing pipelines, and AI integration.
- The role operates at the intersection of data quality, bioinformatics, and dataset creation.
- This is a hands-on technical position with no management responsibilities.
Quelle: öffentlich zugängliche Karriereseite des Arbeitgebers. Batchly ist nicht der Arbeitgeber und steht nicht notwendigerweise in einem Vertragsverhältnis mit dem Unternehmen.