Looking for a job

k f

@kf0

Message

Board-certified PMHNP using AI safety evaluation and medical RLHF to improve clinical accuracy and model guardrails.

United States

Message

What I'm looking for

I’m looking to lead medical RLHF and clinical LLM evaluation work—building ground-truth datasets, safety guardrails, and fine-tuning feedback loops—while applying rigorous psychiatric and neurological clinical reasoning in a safety-first environment.

I’m a Board-Certified Psychiatric Mental Health Nurse Practitioner (DNP, PMHNP-C) with 7+ years of acute clinical practice across psychiatry, pediatric neurology, and behavioral health. I specialize in AI safety evaluation, medical RLHF, and clinical LLM performance optimization—assessing frontier model outputs for logical coherence, factual accuracy, complex reasoning gaps, and safety-critical hallucination patterns.

I’m equally strong in translating clinical criteria into engineering-ready work: prompt adjudication, expert annotation, ground-truth training dataset authorship, and multi-step rationale design for fine-tuning pipelines. Through structured RLHF protocols and rigorous QA, I detect nuanced terminology errors and medical reasoning failures, then generate actionable feedback logs that improve model safety and reliability.

Experience

Work history, roles, and key accomplishments

AI Model Evaluation Project

Mercor

May 2026 - Jun 2026 (1 month)

Assessed frontier LLM outputs for prompt adjudication, advanced STEM evaluation, and clinical reasoning to verify accuracy, safety constraints, and professional tone. Produced structured feedback logs describing multi-step reasoning failures and healthcare risk vectors for RLHF and fine-tuning.

LLM Evaluation Prompt Adjudication Clinical Reasoning Evaluation Medical Safety Constraints Structured Feedback Fine Tuning Multi Step Reasoning

AI Training Specialist

Mercor

May 2026 - Jun 2026 (1 month)

Evaluated frontier LLM outputs using structured RLHF protocols across psychiatric and neurological domains, focusing on clinical logic, factual consistency, and conversational safety. Authored ground-truth training datasets and multi-step reasoning guidelines to improve model alignment and safety.

Medical RLHF LLM Evaluation Prompt Adjudication Hallucination Detection Factual Consistency Checking Fine Tuning Pipelines STEM Content Evaluation

PMHNP Integration Framework

Texas Christian University

Jan 2024 - Jan 2025 (1 year)

Designed and executed a systematic clinical evaluation architecture using the PEPPA Framework to optimize advanced practice nurse utilization in primary care systems. Used quantitative and qualitative research methods to evaluate decision quality and isolate operational variables for institution-scale optimization recommendations.

PEPPA Framework Clinical Evaluation Architecture Quantitative Research Qualitative Research Decision Quality Variable Isolation & QA Technical Writing

PMHNP Clinical Training

John Peter Smith Health Network

Jan 2022 - Jan 2025 (3 years)

Completed psychiatric clinical rotations across Psychiatric Emergency, Consultation-Liaison, and Specialty Behavior settings, building diagnostic and clinical reasoning expertise. Modeled structured verification and red-teaming workflows relevant to rapid AI assessment and evaluation.

Psychiatric Clinical Rotations Psychiatric Emergencies Differential Diagnosis Clinical Reasoning Evaluation Lifespan Diagnostics Red Teaming

Certified Pediatric Nurse

Cook Children's Medical Center

Jan 2019 - Jan 2024 (5 years)

Provided direct inpatient clinical care for complex pediatric neurological patients with behavioral health comorbidities and maintained individualized safety protocols. Collaborated with multidisciplinary teams and maintained high-fidelity EHR documentation.

Epilepsy Monitoring Psychiatry Behavioral Health Crisis Response Differential Diagnosis Technical Writing