AI Red Teamer

JOB DESCRIPTION

Location: India (Remote)

Employment Type: Contract / Part-time

Experience Level: Mid-level and above (flexible for strong AI security background)

Reporting To: Head of Security / Product Lead

Position Summary

We are hiring an experienced AI Red Teamer to identify vulnerabilities and test attack vectors on our platforms. You'll conduct systematic testing, document findings, and work with our team on remediation priorities.

This is a hands-on role for someone with practical experience in prompt injection attacks and the ability to think like an attacker.

Key Responsibilities

Platform Testing

• Conduct prompt injection attacks, jailbreaks, and prompt manipulation tests
• Document attack chains, edge cases, and unexpected behaviors with reproducible steps
• Test across different LLM models and prompt variations

Vulnerability Reporting

 - Identify security gaps and test results

 - Prioritize findings by severity

 - Provide clear, actionable reports with proof-of-concept demonstrations

Collaboration

 - Work with product and engineering teams on testing scope and priorities

 - Present findings clearly

 - Document attack methodologies for internal knowledge base

Testing Framework

 - Develop testing methodologies and frameworks for red teaming

 - Re-test after fixes to verify changes

 - Stay current with emerging AI attack techniques

Required Qualifications

Experience in:

 - AI/LLM security, prompt injection, or jailbreak research (any duration)

 - Red teaming, penetration testing, or offensive security

 - OR demonstrated hands-on capability breaking AI systems

Demonstrated expertise in:

 - Prompt injection techniques (direct, indirect, second-order)

 - LLM behavior exploitation and prompt engineering

 - Attack documentation and vulnerability reporting

Technical skills:

 - Comfortable working with APIs (OpenAI, Anthropic, Hugging Face, etc.)

 - Ability to test and compare outputs across multiple LLM models

 - Basic Python or scripting knowledge (for automation and testing)

 - Version control (Git)

Communication:

 - Ability to document attacks clearly with reproducible steps

 - Comfortable presenting technical findings to non-technical stakeholders

 - Strong written communication for vulnerability reports

Mindset:

 - Creative, adversarial thinking — you see what breaks before it breaks

 - Curiosity about emerging AI security threats

 - Self-directed; comfortable working with ambiguous scopes

Preferred Qualifications

- Published AI security research, blog posts, or public attack demonstrations

- Contributions to open-source security tools (AgentBreaker, jailbreak frameworks, etc.)

- Experience with CTF-style platforms (prompt injection or AI-focused)

- Knowledge of LLM fine-tuning, prompt injection mitigations, or defense mechanisms

- Background in information security, bug bounty programs, or ethical hacking

- Experience with curriculum design or technical training

What We Offer

- Hands-on red teaming work

- Flexible engagement (contract or part-time, no long-term commitment)

- Competitive rates based on experience

Performance Metrics & Success Criteria

You'll be successful if:

- You identify actionable vulnerabilities in platform testing

- Your reports are clear, reproducible, and detailed

- You develop a reusable testing methodology for the team

- You stay current with emerging attack techniques and share findings

To apply:

1. Submit resume + brief cover letter explaining your AI red teaming experience

2. Share portfolio or links to:

  - Public security research / blog posts

  - GitHub profile with relevant projects

  - Examples of vulnerabilities you've found (can be anonymized)

3. In your application, mention: 1-2 prompt injection techniques you're most familiar with

How to Apply

Email: [[HIDDEN TEXT] / hiring contact]

Company Information: KageXis an AI security company.

Learn more: kagex.ai

Equal Opportunity Statement: KageX is an equal opportunity employer. We celebrate diversity and are committed to creating an inclusive environment for all employees, regardless of background, identity, or experience.