AI Security Specialist | $90/hr Remote

Crossing Hurdles; India; Remote; INR 6.548.000 - 11.786.000; Teilzeit

Zusammenfassung

Crossing Hurdles is seeking an AI Security Specialist for a remote contract. You will design methods to test AI safety, including jailbreaks and prompt injections, and build comprehensive evaluation frameworks.

The role requires deep expertise in adversarial ML, LLM red teaming, and clear technical communication. Responsibilities include reporting findings and collaborating with stakeholders to improve model safety.

Qualifikationen

• Experience in adversarial ML, LLM red teaming, and AI safety evaluation.
• Proven research/testing of ethical jailbreaks, prompt injection, and adversarial AI.
• Recognized contributions in AI security through publications or tools.
• Strong written and verbal communication for technical and non-technical audiences.
• Familiarity with current LLM architectures and security assessment tools.

Aufgaben

• Design methodologies to evaluate AI system safety and jailbreak scenarios.
• Create cross-domain strategies to find multi-turn adversarial bypass patterns.
• Develop and maintain regression tests for jailbreaks and prompt-injection.
• Build evaluation frameworks to stress-test models against real threats.
• Translate findings into actionable model safety improvements with stakeholders.
• Document methods and results clearly in reports and presentations.

Kenntnisse

Adversarial ML

LLM red teaming

AI safety evaluation

Technical communication

LLM architectures

Ausbildung

PhD/MS in CS/Cybersecurity/ML

Jobbeschreibung

Position: AI Security Specialist | $90/hr Remote

Type: Contract

Compensation: $50 - $90/hour

Location: Remote

Commitment: 10-40 hrs/week

Role Responsibilities

• Design and implement advanced methodologies for evaluating AI system safety, focusing on ethical jailbreaks, LLM red teaming, prompt injection, and tool-use abuse scenarios.
• Create comprehensive cross-domain elicitation strategies to uncover multi-turn and complex adversarial bypass patterns in AI models.
• Develop, maintain, and update regression test suites that systematically test for jailbreak susceptibility and prompt-injection vulnerabilities.
• Construct robust evaluation frameworks that stress-test AI models against real-world adversarial threats, aiming to enhance overall system robustness.
• Collaborate with technical stakeholders to translate security findings into actionable improvements for model safety and risk mitigation.
• Document methodologies, findings, and best practices in clear, well-structured written reports and presentations for both technical and non-technical audiences.

Requirements

• Have strong relevant experience in adversarial machine learning, LLM red teaming, AI safety evaluation, or a closely related security domain.
• Proven experience researching, testing, or uncovering vulnerabilities related to ethical jailbreaks, prompt injection, tool-use abuse, or adversarial AI attacks.
• Advanced degree (PhD, MS) in computer science, cybersecurity, machine learning, or a relevant discipline, or equivalent operational/professional background.
• High credibility and recognition within the AI security or adversarial ML community such as published research, open-source tools, or conference presentations.
• Exceptional written and verbal communication skills, with a strong focus on clear documentation and collaborative problem-solving.
• Familiarity with current LLM architectures, prompt engineering techniques, and security assessment tools is highly desirable.