Description

You will conduct security reviews and red-team testing for AI systems, including prompts, agents, and multi-agent workflows.

This role is remote.

Responsibilities

• Test for AI attack vectors such as prompt injection, data leakage, model inversion, and jailbreaking.
• Validate compliance with AI security standards, responsible AI frameworks, and data protection requirements.
• Document security findings, non-compliance issues, and recommended mitigations for engineering and leadership teams.
• Monitor updates to AI platforms, models, and frameworks to keep testing criteria current.
• Enhance review processes and create reusable scripts for continuous improvement.

Required Skills

• 5+ years of experience in security testing or AI security.
• Deep understanding of LLMs, vector databases, prompt frameworks, and agent orchestration.
• Experience with AI security testing tools, red-team prompt testing suites, and agent behavior analyzers.
• Ability to evaluate hallucinations, unauthorized data access, and harmful outputs.
• Proficiency in Python and JavaScript for automation and testing scripts.
• Understanding of cloud security on Azure, AWS, or GCP.
• Bachelor’s degree in Computer Science or related field.
• Strong technical writing skills for clear documentation of risks and findings.

Preferred Skills

• Experience with multi-agent workflows and agentic automation tools.
• Familiarity with LLM evaluation frameworks and guardrail systems.

Key Skills

Education

Bachelor's degree