For employers

Hire this AI Trainer

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

Invite to Job
S
Sam J.

Sam J.

Application Security Engineer - AI Model Evaluation & Threat Modeling

USA flagringgold, Usa

Key Skills

Software

No software listed

Top Subject Matter

Application Security
Agentic AI
Threat Modeling

Top Data Types

TextText
DocumentDocument

Top Task Types

No task types listed

Freelancer Overview

Application Security Engineer - AI Model Evaluation & Threat Modeling. Brings 9+ years of professional experience across complex professional workflows, research, and quality-focused execution. Core strengths include Internal, Proprietary Tooling, Codex, Gemini CLI, and Claude Code. Education includes Bachelor of Science, Western Governors University (2025). AI-training focus includes data types such as Computer Code, Programming, and Text and labeling workflows including Evaluation and Rating.

Labeling Experience

Application Security Engineer - AI Model Evaluation & Threat Modeling

I evaluated AI security models and agentic AI processes to assess accuracy and reliability in addressing application security risks. I designed and tested internal workflows using MCP-based automation and AI-assisted threat modeling, generating structured outputs such as DFDs, trust boundaries, and mitigation recommendations. My work included AI output evaluation and iterating workflows in collaboration with security architects to enhance secure development life cycle processes. • Reviewed and rated AI-generated outputs for vulnerability triage and secure coding recommendations. • Designed and tested an agentic AI threat modeling skill with iterative feedback. • Implemented AI-driven workflows for automated threat modeling and risk evaluation. • Partnered on rubric design for defensible evaluation of AI security reasoning.

2024 - Present

LLM Security Output Evaluator (Microsoft Copilot Pilot)

TextText

Participated in Microsoft 365 Copilot security evaluation by assessing model outputs for prompt injection, data leakage, and sensitive content labeling gaps. Tasks included testing for safe output generation and alignment with organizational security requirements. Reviewed the effectiveness of sensitivity labeling, risk of prompt injection, and potential for harmful data exfiltration in LLM-generated responses. • Evaluated AI-generated text for security vulnerabilities and sensitive content exposure. • Rated model robustness against prompt injection and phishing risks. • Reviewed and categorized LLM outputs for compliance with sensitivity labeling policies. • Documented findings and recommended improvements based on evaluation results.

2022 - 2024

Education

W

Western Governors University

Bachelor of Science, Computer Science

Bachelor of Science
2025 - 2025

Work History

R

RxSense

Application Security Engineer

Remote
2024 - Present
W

WebstaurantStore

Application Security Engineer

Remote
2022 - 2024