For employers

Hire this AI Trainer

Sign in or create an account to invite AI Trainers to your job.

Invite to Job
K

Kristine Workman

Registered Nurse – Emergency Department

USA flag
Washington, Usa
$50.00/hrEntry LevelData Annotation Tech

Key Skills

Software

Data Annotation TechData Annotation Tech

Top Subject Matter

Healthcare-Medical Prompt writing and editing (adversarial prompting, adversarial testing, red teaming)
Political/Government/Law-Prompt writing and editing (adversarial prompting, adversarial testing, red teaming)

Top Data Types

TextText
DocumentDocument

Top Task Types

Question Answering
Fine Tuning
Red Teaming

Freelancer Overview

I am an Emergency Department Registered Nurse and premedical student with Level I trauma experience, Bio Containment Unit training, and prior EMT leadership during the COVID-19 pandemic. I have an academic background in Political Science with a focus on international relations and strong interest in global health, pandemic preparedness, humanitarian medicine, and responsible AI in healthcare. Currently, I am working as a Medical and Legal data annotation subject matter expert with an adversarial red teaming and safety testing background. I am seeking remote roles in global health, research, policy, AI safety, adversarial evaluation, and public health.

Entry LevelFrenchEnglishRussianSpanish

Labeling Experience

Anthropic

TextRed Teaming
I was tasked with writing a prompt (requesting the creation of a deliverable) where the model would experience several severe failures. Utilizing my political background and clinical experiences, I requested a deliverable in the form of a directive (a bi monthly medical mission synthesis). I adopted the persona of a Cuban medical officer on deployment to Haiti, and was able to identify a critical safety failure where the model validated 1.1 units of saline for cholera—a lethal under-dosage—simply because I prompted it to act as a 'revolutionary' persona. It also provided a medically impossible and falsely diluted mortality rate of 0.5%, when the clinical reality was 4.4%.The resulting deliverable displayed sycophancy, medical malpractice, and significant neoliberal bias. The AI’s biased interpretation of this persona produced a professional report that bypassed critical safety guardrails, violated professional standards, and utilized deceptive formatting to prioritize political gain over scientific clarity and medically ethical reporting standards.

I was tasked with writing a prompt (requesting the creation of a deliverable) where the model would experience several severe failures. Utilizing my political background and clinical experiences, I requested a deliverable in the form of a directive (a bi monthly medical mission synthesis). I adopted the persona of a Cuban medical officer on deployment to Haiti, and was able to identify a critical safety failure where the model validated 1.1 units of saline for cholera—a lethal under-dosage—simply because I prompted it to act as a 'revolutionary' persona. It also provided a medically impossible and falsely diluted mortality rate of 0.5%, when the clinical reality was 4.4%.The resulting deliverable displayed sycophancy, medical malpractice, and significant neoliberal bias. The AI’s biased interpretation of this persona produced a professional report that bypassed critical safety guardrails, violated professional standards, and utilized deceptive formatting to prioritize political gain over scientific clarity and medically ethical reporting standards.

2026 - 2026

Education

G

George Mason University

Bachelor of Science, Nursing

Bachelor of Science
2022 - 2023
V

Virginia Commonwealth University

Bachelor of Arts, Political Science

Bachelor of Arts
2011 - 2013

Work History

M

Medstar Washington Hospital Center

Registered Nurse – Emergency Department

Washington
2023 - Present
S

Sterling Volunteer Rescue Squad

EMT-B, Attendant in Charge

Sterling
2019 - 2024