Scientist – Large Libraries (Protein Screening)

About the role

CradleBio is building an AI‑guided platform for protein discovery and optimization. As a Scientist on the Large Libraries team you will develop high‑throughput screening methods to measure protein‑protein interaction affinities and generate large‑scale datasets that power our machine‑learning models.

Key responsibilities

• Design, build and optimise in‑vitro or cell‑based assay pipelines across multiple display modalities (yeast, phage, mRNA, ribosome or mammalian).
• Develop molecular biology and biochemistry workflows for library construction, screening and data generation at scale.
• Establish robust, statistically‑rigorous assays suitable for ML model training and evaluation.
• Lead projects from experimental design through data delivery, identifying opportunities to improve throughput and data quality.
• Collaborate with the ML team to define data requirements and integrate experimental outputs into the AI pipeline.
• Communicate results and technical challenges across cross‑functional teams and contribute to the scientific direction of the Large Libraries group.

Required profile

• PhD in biochemistry, molecular biology, biophysics, synthetic biology, bioengineering or a related discipline.
• Proven creativity in method development, having invented or substantially adapted experimental workflows.
• Strong written and verbal communication skills in English and ability to work in a fast‑paced, ambiguous startup environment.
• Demonstrated ability to manage multiple projects simultaneously while maintaining thorough documentation and data organisation.

Required skills

• Large‑scale DNA library construction (>10^6 variants).
• Experience with display platforms such as yeast, phage, mRNA, ribosome or mammalian display.
• Flow cytometry and FACS.
• Binding kinetic measurement techniques (SPR, BLI, ELISA).
• Next‑generation sequencing library preparation and analysis (Illumina, Nanopore, PacBio).
• Statistically rigorous experimental design and data quality assessment.
• High‑throughput data analysis and scripting (Python, R).
• Laboratory automation (robotic liquid handlers, plate readers, colony pickers).