AI/ML Scientist, Computational Biologist (P4020)

Planet Pharma; Redwood City (CA); Sur place; USD 96 000 - 165 000; Plein temps

Résumé du poste

Planet Pharma is seeking a hands-on AI/ML Scientist specializing in computational biology on a contract basis in California. The role collaborates with bioinformatics and team scientists to design analyses for downstream machine learning, focusing on AP-MS data, profile similarity, and batch effect control.

You will build reproducible analyses, document methods and assumptions, and ensure data preprocessing preserves biological information while meeting project goals.

Qualifications

• Degree in computational biology, bioinformatics, statistics, quantitative biological science, or a related field, or equivalent research experience.
• Demonstrated experience analyzing biological assay data and translating scientific requirements into practical analytical workplans.
• Strong statistical judgment in assessing reproducibility, experimental controls, batch effects, and measurement uncertainty.
• Proficiency in Python or R, with experience building reproducible analyses, maintaining code in Git, and documenting methods.
• Experience assessing data quality, missingness, preprocessing assumptions, and the suitability of datasets for downstream analysis.
• Working knowledge of machine learning validation, including held-out evaluation, confounding, and risks of information leakage.
• Ability to explain uncertainty and analytical tradeoffs clearly and collaborate effectively with bioinformaticians, chemists, and biologists.
• Ability to independently execute defined work, meet agreed milestones, incorporate feedback, and handle internal data securely.

Responsabilités

• Work with bioinformatics and team scientists to define analytical requirements, deliverables, milestones, and acceptance criteria for experimental data that will be used for machine learning.
• Assess AP-MS profile similarity and technical reproducibility, considering quantitative support, missingness, controls, and uncertainty.
• Evaluate plate and batch effects, distinguishing technical variation from biological differences and experimental confounding.
• Support reference-panel pilot design and assess scoring and normalization approaches against agreed validation criteria for AP-MS and other data types.
• Assess whether preprocessing preserves biological information and produces suitable inputs for downstream modeling.
• Build reproducible analyses and document methods, assumptions, limitations, and provenance.
• Support scientific data evaluation and benchmark design as needed.
• Communicate findings and unresolved questions, coordinate follow-up with bioinformatics, and align analytical work with team needs.

Connaissances

Python

R

Git

Statistics

Data quality

ML validation

Communication

Independent work

Formation

Computational biology, bioinformatics, statistics or related field

Outils

AP-MS

Description du poste

AI/ML Scientist, Computational Biologist

The Opportunity:

Seeking a hands-on Contract AI/ML Scientist to assess scientific data and analytical methods supporting downstream machine learning. The primary focus is computational biology and partnership with bioinformatics on affinity purification mass spectrometry (AP-MS), including profile similarity, technical reproducibility, and batch effects. This individual contributor will coordinate analytical requirements and ensure bioinformatics deliverables meet agreed modeling needs, with flexibility to support computational biology requirements for other projects.

Responsibilities:

• Work with bioinformatics and team scientists to define analytical requirements, deliverables, milestones, and acceptance criteria for experimental data that will be used for machine learning.

• Assess AP-MS profile similarity and technical reproducibility, considering quantitative support, missingness, controls, and uncertainty.

• Evaluate plate and batch effects, distinguishing technical variation from biological differences and experimental confounding.

• Support reference-panel pilot design and assess scoring and normalization approaches against agreed validation criteria for AP-MS and other data types.

• Assess whether preprocessing preserves biological information and produces suitable inputs for downstream modeling.

• Build reproducible analyses and document methods, assumptions, limitations, and provenance.

• Support scientific data evaluation and benchmark design as needed.

• Communicate findings and unresolved questions, coordinate follow-up with bioinformatics, and align analytical work with team needs.

Required Skills, Experience and Education:

• Degree in computational biology, bioinformatics, statistics, quantitative biological science, or a related field, or equivalent research experience.

• Demonstrated experience analyzing biological assay data and translating scientific requirements into practical analytical workplans.

• Strong statistical judgment in assessing reproducibility, experimental controls, batch effects, and measurement uncertainty.

• Proficiency in Python or R, with experience building reproducible analyses, maintaining code in Git, and documenting methods.

• Experience assessing data quality, missingness, preprocessing assumptions, and the suitability of datasets for downstream analysis.

• Working knowledge of machine learning validation, including held-out evaluation, confounding, and risks of information leakage.

• Ability to explain uncertainty and analytical tradeoffs clearly and collaborate effectively with bioinformaticians, chemists, and biologists.

• Ability to independently execute defined work, meet agreed milestones, incorporate feedback, and handle internal data securely.

Preferred Skills:

• Advanced degree in computational biology, bioinformatics, statistics, or a related field.

• Experience with quantitative proteomics, AP-MS, or other high-dimensional biological profiling assays.

• Experience comparing profile similarity, control-relative scoring, batch correction, or reference-panel validation methods.

• Experience with drug discovery, DEL analysis, scientific evidence evaluation, or collaboration between bioinformatics and ML teams.

• Experience with Databricks, cloud/HPC workflows, or computational projects in biotechnology.