Data selection and quality evaluation for biological foundation models

About the role

Inceptive is building large-scale foundation models for molecular design and AI-driven drug discovery. This role involves collaborating with biologists and machine learning researchers to design, analyze, and improve the experiments that generate high-quality data for these models. You will help identify measurement artifacts and translate biological insights into scalable data generation strategies.

Responsibilities

• Develop statistical and computational approaches to characterize assay quality, reproducibility, and sources of experimental variation
• Identify and investigate sources of bias and measurement artifacts in biological datasets
• Design and analyze large-scale biological experiments that generate training and evaluation data for machine learning models
• Partner with experimental scientists to improve assay design, controls, and data collection strategies
• Collaborate with machine learning researchers to understand how experimental design decisions impact model training and evaluation
• Analyze, visualize, and communicate findings to support decision-making across scientific and engineering teams

Required skills

• Computational biology
• Experimental design
• Statistical analysis
• Python
• Scientific computing

Nice to have

• Biostatistics
• Machine learning model development

Qualifications

• PhD in computational biology, systems biology, genomics, bioengineering, biostatistics, biophysics, or a related quantitative discipline
• Equivalent practical experience

Benefits

• 30 days paid vacation
• Health insurance
• 401K with company match
• Direktversicherung
• Quarterly company-wide retreats
• Monthly wellness benefit
• Learning & Development budget

About the Company

Inceptive creates tools to develop biological software for the rational design of novel medicines and biotechnologies. The team combines expertise in molecular biology, machine learning, and software engineering to pioneer a new discipline rooted in both biology and deep learning.