Postdoc: Vision Models for AI Imaging in Drug Discovery

Scorpion Therapeutics; San Diego (CA); On-site; USD 78,000 - 96,000; Full time

Benefits offered by this job

Health benefits

401(k) match

Time off

Job summary

Scorpion Therapeutics seeks a scientist to develop vision foundation models for high-content cellular imaging, advancing self-supervised learning and multimodal integration for drug discovery. You will design robust evaluation protocols and contribute to scalable, reproducible training pipelines on HPC and cloud.

The ideal candidate holds a PhD, has publications or patents, and demonstrates strong Python and deep learning framework skills with independent research drive and collaboration across

Qualifications

• PhD completed before start date with demonstrated scientific achievement.
• Strong Python and deep learning framework experience; GPU training.
• Experience on HPC or cloud with reproducible code.

Responsibilities

• Develop vision foundation models for high-content cellular imaging using self-supervised learning.
• Design evaluation protocols to measure generalization across assays, perturbations, cell types, and imaging conditions.
• Curate large-scale microscopy datasets and establish data quality standards.
• Extend models to multimodal settings integrating imaging with other data for drug discovery.
• Build scalable, reproducible training and inference pipelines across HPC and cloud.
• Propose innovative methods and publish/present results.

Skills

Python

PyTorch

TensorFlow

JAX

HPC

Cloud

Vision foundation models

Self-supervised learning

Research independence

Publications

Education

PhD in a relevant field

Tools

MLflow

Git

Job description

Scorpion Therapeutics seeks a scientist to develop vision foundation models for high-content cellular imaging, advancing self-supervised learning and multimodal integration for drug discovery. You will design robust evaluation protocols and contribute to scalable, reproducible training pipelines on HPC and cloud.

The ideal candidate holds a PhD, has publications or patents, and demonstrates strong Python and deep learning framework skills with independent research drive and collaboration across