This job post has expired on August 12, 2026. It is likely that the position has already been filled.
AI Jailbreak & Prompt Injection Expert at micro1
posted 3 months agoAI Jailbreak & Prompt Injection Security Expert | $50–90/hr | Worldwide Remote
Join MICRO1 as a specialized cybersecurity contractor focused on AI and large language model (LLM) security. In this role, you will probe, stress-test, and harden AI systems against adversarial attacks — helping ensure that cutting-edge AI products are safe, robust, and resilient.
Key Responsibilities
- Conduct ethical jailbreak testing on LLMs to identify exploitable vulnerabilities
- Design and execute prompt injection attack scenarios to assess model susceptibility
- Perform red teaming exercises targeting LLM-based applications and pipelines
- Investigate and document tool-use abuse vectors within AI agent frameworks
- Provide actionable remediation recommendations and security reports
- Collaborate with AI and engineering teams to implement security best practices
Required Skills
- Ethical Jailbreaking: Hands-on experience bypassing AI safety guardrails in a controlled, responsible manner
- LLM Red Teaming: Proven ability to simulate adversarial attacks on language models
- Prompt Injection: Deep understanding of injection techniques and their real-world implications
- Tool-Use Abuse: Familiarity with exploiting agentic AI tool-calling mechanisms
Compensation & Details
- Rate: $50–$90/hr (based on experience)
- Engagement: Contract / Freelance
- Location: Fully Remote — open worldwide
If you are passionate about AI security and want to be at the forefront of responsible AI development, we encourage you to apply.