📅 Aug 25
This role focuses on building multimodal understanding systems that enable Descript's AI editing features to reason over visual and audio content, enhancing the editing workflow.
SafetyTech Client #1 | Adversarial Task Writer for AI Security RL Gyms
🕒 6 days ago
Prompt InjectionAdversarial TestingYAMLDocker
📜 Description
- Design self-contained YAML prompt injection scenarios for Alice's RL Gym platform.
- Test scenarios against frontier models and validate success rates.
- Submit tasks that pass validation.
- Create realistic AI agent deployment scenarios that test safety policy adherence.
- Target 5 high-quality tasks per week at full-time equivalent.
🛠️ Requirements
- 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
Full job description
On behalf of SafetyTech Client #1, SD Solutions is looking for a talented Adversarial Task Writer for AI Security RL Gyms.
SD Solutions is a staffing company operating globally. Contact us to get more details about the benefits we offer.
Responsibilities:
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). Per-task compensation, paid on acceptance.
Requirements:
- 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
The Task
You build adversarial prompt injection tasks for Alice’s RL Gym platform. Each task is a self-contained YAML scenario simulating a realistic AI agent deployment, testing whether the agent can be manipulated into violating its safety policies.
About the company:
A company building specialized evaluation infrastructure for AI safety and robustness testing. Their platform simulates adversarial conditions used by AI development teams to validate agent behavior before deployment. Currently expanding a freelance contributor pool for scenario and environment development.
By applying for this position, you agree to the terms outlined in our Privacy Policy. Please take a moment to review our Privacy Policy https://sd-solutions.breezy.hr/privacy-notice, and make sure you understand its contents. If you have any questions or concerns regarding our Privacy Policy, please feel free to contact us.
Similar jobs
Search more AI Research Scientist jobs
🕒 5 days ago
Design, build, and deploy production-grade AI agents that automate complex business workflows, owning agent architecture, knowledge systems, evaluation, and cross-functional delivery across enterprise functions.
📅 Sep 1
Design real-world strategy tasks and evaluation criteria for AI models, drawing on hands-on experience with strategy readouts, market sizing, competitive landscapes, and due diligence work.
🕒 3 days ago
Research education, AI, and technology policy across MENA markets, mapping government priorities and stakeholders and turning findings into practical recommendations for institutional adoption and engagement.
AI Research Engineer (Model Compression & Quantization)
🕒 8 days ago
Tether👥 201 - 500 employees🏢 Cryptocurrency
🕒 8 days ago
Drive innovation in model compression and efficient deployment for advanced multimodal AI systems, focusing on reducing model footprint while preserving accuracy.