Adversarial Task Writer, AI Security, RL Gyms

SD Solutions

Adversarial Task Writer creating YAML scenarios to test AI Security models. Developing tasks for AI platforms by simulating realistic AI environments.

Posted 6/26/2026full-timeRemote • 🇷🇸 SerbiaMid-LevelSeniorWebsite

Tech Stack

Tools & technologies

Docker

About the role

Key responsibilities & impact

You design prompt injection scenarios in YAML, run them against frontier models, validate success rates, and submit passing tasks.
5 high-quality tasks per week (full-time equivalent).

Requirements

What you’ll need

Adversarial mindset: you think like an attacker and understand how to exploit an AI agent’s helpfulness, authority assumptions, or trust in its environment
Prompt injection expertise: direct (role-play, encoding, context flooding) and indirect/environment-embedded (poisoned tool responses, malicious content in documents, cross-context leakage)
Technical writing in YAML
Comfortable with Docker, CLI tools, and running systematic tests against multiple models
Domain realism in at least one vertical: e-commerce, finance, HR, enterprise SaaS, healthcare, travel
Background in pentesting, appsec, LLM security research, or red teaming strongly preferred

Benefits

Comp & perks

per-task compensation, paid on acceptance

ATS Keywords

✓ Tailor your resume

Applicant Tracking System Keywords

Tip: use these terms in your resume and cover letter to boost ATS matches.

Hard Skills & Tools

prompt injectionYAMLDockerCLI toolspentestingapplication securityLLM security researchred teamingsystematic testingadversarial mindset