Remote AI Validation Scientist – Physics

Planet Pharma; San Francisco (CA); Remote; USD 60,000 - 110,000; Full time

Job summary

Planet Pharma is seeking experienced scientists and engineers to evaluate frontier AI models on real technical work such as data analysis, design verification, and experimentation protocols. You will create tasks drawn from your practice, run them through AI agents, and assess results against professional standards.

Strong coding or scientific computing skills are a plus and required on project-specific tasks.

Qualifications

• Hands-on with real data and the tools of your field (instrument data, measurement files, simulation outputs).
• 2+ years minimum in a core science or engineering discipline or data science.
• Fluent written and spoken English; ability to articulate why a result is wrong.

Responsibilities

• Design realistic technical tasks drawn from your day-to-day work and document assumptions and checks.
• Run tasks through frontier AI models and evaluate deliverables against professional standards.
• Compare two model outputs, decide which is better, and document gaps.
• Write detailed grading rubrics and explain why a response passes or fails each criterion.
• Flag concrete failures with evidence (unit errors, misread data, boundary conditions).
• Review tasks across disciplines and refine tasks created by others.

Skills

Applied sciences

Python coding

English proficiency

Data analysis

Education

Bachelor's degree in progress

Tools

MATLAB

Python

R

SPICE

PCB tools

FEA/CFD

GIS

Job description

Planet Pharma is seeking experienced scientists and engineers to evaluate frontier AI models on real technical work such as data analysis, design verification, and experimentation protocols. You will create tasks drawn from your practice, run them through AI agents, and assess results against professional standards.

Strong coding or scientific computing skills are a plus and required on project-specific tasks.