> Markdown version of [/jobs/ext/4482414-scientist-machine-learning-ai](https://www.wearedevelopers.com/jobs/ext/4482414-scientist-machine-learning-ai). Every page supports `.md` or `Accept: text/markdown`. Links point to the HTML versions so they work for humans too. Agent guide: [/agents.md](https://www.wearedevelopers.com/agents.md).

---

# Scientist, Machine Learning AI

- **Company:** Katalyst Talent Agency
- **Location:** United States (Remote available)
- **Contract:** Permanent contract
- **Skills:** Training Data, Artificial Intelligence, Bioinformatics, Computational Biology, Python (Programming Language), Machine Learning, Scientific Computating, Systems Integration, Unstructured Data, Feature Engineering, Model Validation
- **Published:** October 27, 2026
- **Apply:** https://www.careerbuilder.com/job-details/scientist-machine-learning-ai--2c0c4cee-c629-4f76-9433-60f72655fd8d

## About the Role

Machine Learning, Artificial Intelligence (AI), Training Data Sets, Machine Learning, Unstructured Data, Quality Control, Structured Data, Performance Reviews, Performance Analysis, Model Validation, * Advanced degree (M.S. or Ph.D.) in computational biology, bioinformatics, computational chemistry, biophysics, or a related field.

 * Hands-on experience applying machine learning to biological, chemical, or biomedical data.
 * Experience working with protein structure data and/or structure-derived features in a research or drug discovery setting.
 * Experience integrating or modeling phenotypic and multimodal datasets.
 * Strong Python programming skills and experience with scientific computing and machine-learning libraries.
 * Ability to independently execute defined project work and deliver high-quality outputs on an agreed timeline.

## Description

* Develop and apply machine-learning and statistical approaches to protein structure, phenotypic, and other multimodal biological datasets.
 * Curate, harmonize, and quality-control structured and unstructured data from internal and external sources.
 * Build reproducible computational workflows for feature generation, model training, validation, and performance evaluation.
 * Integrate protein structural representations with phenotypic and other biological data to generate testable hypotheses and prioritize follow-up analyses.
 * Implement clear, maintainable analysis code and contribute to shared repositories and technical documentation.
 * Communicate methods, findings, and recommendations clearly to technical and non-technical stakeholders.