inceptive
Data selection and quality evaluation for biological foundation models
$135K–$240K
Berlin, Germany or Palo Alto, CA or Zurich, Switzerland +3 · Full-time · Posted Jul 16, 2026
- Location
- Berlin, Germany or Palo Alto, CA or Zurich, Switzerland
Berlin, Berlin, Germany
Palo Alto, California, United States
Zürich, Zürich, Switzerland - Experience
- Preferred: 3+ years of post-PhD experience in computational biology, biostatistics, or a related field.
- Education
- PhD in computational biology, systems biology, genomics, bioengineering, biostatistics, biophysics, or a related quantitative discipline, or equivalent practical experience.
About the job
Design and analyze biological experiments and datasets to assess data quality and generate reliable training and evaluation data for biological foundation models.
What you'll do
- Develop statistical and computational approaches to assess assay quality, reproducibility, variation, bias, and artifacts.
- Design and analyze biological experiments; partner with scientists to improve assay design, controls, and data collection.
- Collaborate with machine learning researchers and communicate findings that inform model training and evaluation.
What they ask for
- PhD in a related quantitative discipline, or equivalent practical experience.
- Track record analyzing complex biological datasets and translating computational insights into experimental validation or new data collection.
- Strong foundation in experimental design, statistical analysis, and quantitative reasoning; deep understanding of biological data variability, batch effects, and assay artifacts.
- Capable programmer in Python and common scientific computing libraries.
Nice to have
- 3+ years of post-PhD experience in computational biology, biostatistics, or a related field.
- Experience connecting experimental outcomes to machine learning model development and evaluation.
Pay
$135K – $240K USD base salary; bonus and equity amounts not stated.
Tools
Python
AI focus
Generate and evaluate high-quality biological data for foundation-model training; connect experimental design and outcomes to machine learning model development and evaluation.
Model-written summary · the original posting is authoritative