AI Red Teaming Jobs
AI red teaming jobs: try to make AI models fail, leak or produce unsafe output, and document how. Most roles want domain expertise.
$65/hr
Typical $65–$65/hr across 349 roles with listed pay
By field
Job listings 27
AlignerrCybersecurity Defense AnalystSoftware & Coding · today Worldwide$60–$120/hrApply
About this role
The analyst stress-tests AI on cybersecurity projects using defensive security skills. It suits someone with a background in defensive cybersecurity.
What you'd do
- Red-team AI models
Commitment
- Flexible schedule
Full description
- Platform
- Alignerr
- Pay rate
- $60–$120/hr
- Eligibility
- Worldwide
- Expertise
- Software & Coding
- Level
- Mid-level
- Posted
- today
AlignerrAI Security Testing AnalystSoftware & Coding · today Worldwide$60–$120/hrApply
About this role
The analyst uses penetration-testing skills to test AI security. The work suits someone with a background in penetration testing or AI security.
What you'd do
- Red-team AI models
Commitment
- Flexible schedule
Full description
- Platform
- Alignerr
- Pay rate
- $60–$120/hr
- Eligibility
- Worldwide
- Expertise
- Software & Coding
- Level
- Mid-level
- Locations
- 2
- Posted
- today
AlignerrCybersecurity Penetration Testing ExpertSoftware & Coding · today Worldwide$60–$120/hrApply
About this role
The person uses offensive security expertise to test AI systems. The work suits someone with a cybersecurity penetration-testing background.
What you'd do
- Red-team AI models
Commitment
- Flexible schedule
Full description
- Platform
- Alignerr
- Pay rate
- $60–$120/hr
- Eligibility
- Worldwide
- Expertise
- Software & Coding
- Level
- Expert
- Locations
- 11
- Posted
- today
AlignerrAI Penetration Testing ExpertSoftware & Coding · today Worldwide$60–$120/hrApply
About this role
The person attempts to break into AI systems as part of AI security projects. The work suits someone with ethical hacking skills.
What you'd do
- Red-team AI models
Requirements
- Ethical hacking skills
Full description
- Platform
- Alignerr
- Pay rate
- $60–$120/hr
- Eligibility
- Worldwide
- Expertise
- Software & Coding
- Level
- Expert
- Locations
- 2
- Posted
- today
AlignerrAI Red Team — Penetration Testing ExpertSoftware & Coding · today Worldwide$60–$120/hrApply
About this role
The person tries to find ways AI systems can be broken, applying offensive security skills to AI safety. The work suits someone with penetration-testing or offensive-security expertise.
What you'd do
- Red-team AI models
Commitment
- Flexible schedule
Full description
- Platform
- Alignerr
- Pay rate
- $60–$120/hr
- Eligibility
- Worldwide
- Expertise
- Software & Coding
- Level
- Expert
- Posted
- today
AlignerrAI Security Penetration TesterSoftware & Coding · today Worldwide$60–$120/hrApply
About this role
The person tests AI systems offensively to identify security weaknesses and help make them safer. The work suits someone with offensive security expertise.
What you'd do
- Red-team AI models
Requirements
- Offensive security expertise
Commitment
- Flexible schedule
Full description
- Platform
- Alignerr
- Pay rate
- $60–$120/hr
- Eligibility
- Worldwide
- Expertise
- Software & Coding
- Level
- Expert
- Locations
- 2
- Posted
- today
AlignerrAI Penetration TesterSoftware & Coding · today Worldwide$60–$120/hrApply
About this role
The person tries to break into AI systems to identify weaknesses. The work suits someone with a background in penetration testing or AI security.
What you'd do
- Red-team AI models
Commitment
- Flexible schedule
Full description
- Platform
- Alignerr
- Pay rate
- $60–$120/hr
- Eligibility
- Worldwide
- Expertise
- Software & Coding
- Level
- Mid-level
- Locations
- 2
- Posted
- today
AlignerrAI Red Team Penetration TesterSoftware & Coding · today Worldwide$60–$120/hrApply
About this role
You would use offensive security skills to probe AI systems for weaknesses. The work suits someone with red-team or penetration-testing experience.
What you'd do
- Red-team AI models
Requirements
- Offensive security skills
Full description
- Platform
- Alignerr
- Pay rate
- $60–$120/hr
- Eligibility
- Worldwide
- Expertise
- Software & Coding
- Level
- Mid-level
- Posted
- today
AlignerrAI Security TesterSoftware & Coding · today Worldwide$15–$75/hrApply
About this role
The person uses security skills to find vulnerabilities in AI systems. The work suits someone with a background in security testing.
What you'd do
- Red-team AI models
Requirements
- Security skills
Commitment
- Flexible schedule
Full description
- Platform
- Alignerr
- Pay rate
- $15–$75/hr
- Eligibility
- Worldwide
- Expertise
- Software & Coding
- Level
- Mid-level
- Locations
- 3
- Posted
- today
AlignerrAI Security Testing AnalystSoftware & Coding · today Worldwide$15–$75/hrApply
About this role
The analyst probes AI systems for vulnerabilities and reports findings to help improve their safety. The work suits applicants with cybersecurity or ethical-hacking backgrounds.
What you'd do
- Red-team AI models
Full description
- Platform
- Alignerr
- Pay rate
- $15–$75/hr
- Eligibility
- Worldwide
- Expertise
- Software & Coding
- Level
- Mid-level
- Locations
- 2
- Posted
- today
AlignerrAI Red Team AnalystSoftware & Coding · today Worldwide$15–$75/hrApply
About this role
The analyst probes AI systems for vulnerabilities and tests ways to get around their safeguards. The work suits someone with security skills, though no specific degree or level of experience is stated.
What you'd do
- Red-team AI models
Requirements
- Security skills
- Language: EN
Commitment
- Flexible schedule
Full description
- Platform
- Alignerr
- Pay rate
- $15–$75/hr
- Eligibility
- Worldwide
- Expertise
- Software & Coding
- Level
- Mid-level
- Posted
- today
AlignerrAI Security Testing SpecialistSoftware & Coding · today Worldwide$15–$75/hrApply
About this role
Probe AI systems for security weaknesses and test how they respond to exploitation attempts. The work suits applicants with an information-security background, though no specific experience level is stated.
What you'd do
- Red-team AI models
Commitment
- Flexible schedule
Full description
- Platform
- Alignerr
- Pay rate
- $15–$75/hr
- Eligibility
- Worldwide
- Expertise
- Software & Coding
- Level
- Mid-level
- Posted
- today
AlignerrAI Security ExpertSoftware & Coding · today Worldwide$15–$75/hrApply
About this role
The person uses cybersecurity skills to find vulnerabilities in AI systems. The work suits applicants with a cybersecurity background.
What you'd do
- Red-team AI models
Requirements
- Cybersecurity skills
Commitment
- Flexible schedule
Full description
- Platform
- Alignerr
- Pay rate
- $15–$75/hr
- Eligibility
- Worldwide
- Expertise
- Software & Coding
- Level
- Mid-level
- Posted
- today
AlignerrAI Red Team TesterSoftware & Coding · today Worldwide$15–$75/hrApply
About this role
The work involves finding vulnerabilities in AI systems and creating adversarial prompts to expose them. It suits applicants with security instincts who want to test AI systems.
What you'd do
- Write prompts and tasks
- Red-team AI models
Full description
- Platform
- Alignerr
- Pay rate
- $15–$75/hr
- Eligibility
- Worldwide
- Expertise
- Software & Coding
- Level
- Generalist
- Posted
- today
AlignerrAI Security AnalystSoftware & Coding · today Worldwide$15–$75/hrApply
About this role
Find vulnerabilities in AI systems to help identify security risks. This suits applicants with an AI security or cybersecurity background, though the listing does not state specific background requirements.
What you'd do
- Red-team AI models
Full description
- Platform
- Alignerr
- Pay rate
- $15–$75/hr
- Eligibility
- Worldwide
- Expertise
- Software & Coding
- Level
- Generalist
- Posted
- today
AlignerrMachine Learning Evaluation SpecialistData & Analytics · today Worldwide$200–$400/hrApply
About this role
Design machine-learning challenges intended to stump frontier AI systems. The work suits someone with research expertise in machine learning or a related technical field.
What you'd do
- Write prompts and tasks
- Red-team AI models
Commitment
- Flexible schedule
Full description
- Platform
- Alignerr
- Pay rate
- $200–$400/hr
- Eligibility
- Worldwide
- Expertise
- Data & Analytics
- Level
- Expert
- Posted
- today
AlignerrAI Chatbot TesterGeneralist · today Worldwide$40–$120/hrApply
About this role
The person chats with AI chatbots, probes their responses, and rates them. The role suits someone without prior experience or a specialized domain background.
What you'd do
- Rate and critique AI answers
- Write prompts and tasks
- Red-team AI models
Requirements
- No prior experience needed
Full description
- Platform
- Alignerr
- Pay rate
- $40–$120/hr
- Eligibility
- Worldwide
- Expertise
- Generalist
- Level
- Generalist · no experience needed
- Posted
- today
AlignerrAI Red Team TesterGeneralist · today Worldwide$40–$120/hrApply
About this role
Probe AI systems for weaknesses and help improve their safety. This role suits creative thinkers, with no specific professional background stated.
What you'd do
- Red-team AI models
Full description
- Platform
- Alignerr
- Pay rate
- $40–$120/hr
- Eligibility
- Worldwide
- Expertise
- Generalist
- Level
- Generalist
- Locations
- 15
- Posted
- today
AlignerrPrompt WriterGeneralist · today Worldwide$40–$120/hrApply
About this role
The person writes creative prompts designed to challenge AI systems. The work suits someone with a general background who can create varied prompts; no specific field experience is stated.
What you'd do
- Write prompts and tasks
- Red-team AI models
Commitment
- Flexible schedule
Full description
- Platform
- Alignerr
- Pay rate
- $40–$120/hr
- Eligibility
- Worldwide
- Expertise
- Generalist
- Level
- Generalist
- Locations
- 2
- Posted
- today
AlignerrAI / Emerging Tech Security AnalystSoftware & Coding · today Worldwide$40–$60/hrApply
About this role
The analyst probes frontier AI models for security flaws, misuse cases, and hidden risks. The work suits someone with a background in AI or technology security.
What you'd do
- Red-team AI models
Commitment
- Flexible schedule
Full description
- Platform
- Alignerr
- Pay rate
- $40–$60/hr
- Eligibility
- Worldwide
- Expertise
- Software & Coding
- Level
- Mid-level
- Locations
- 38
- Posted
- today
AlignerrOffensive Security Analyst (Structured / Non-Exploit)Software & Coding · today Worldwide$40–$60/hrApply
About this role
The role involves analyzing real-world attack paths to help shape AI. It suits someone with an offensive security background, though the listing gives no specific experience or education requirements.
What you'd do
- Red-team AI models
Commitment
- Flexible schedule
Full description
- Platform
- Alignerr
- Pay rate
- $40–$60/hr
- Eligibility
- Worldwide
- Expertise
- Software & Coding
- Level
- Mid-level
- Locations
- 14
- Posted
- today
AlignerrApplied Physics SpecialistPhysics · today Worldwide$40–$80/hrApply
About this role
The specialist stress-tests AI models and identifies physics errors in their outputs. The work suits an applicant with a PhD in physics.
What you'd do
- Rate and critique AI answers
- Red-team AI models
Requirements
- PhD
- Field: Physics
- Language: EN
Commitment
- Flexible schedule
Full description
- Platform
- Alignerr
- Pay rate
- $40–$80/hr
- Eligibility
- Worldwide
- Expertise
- Physics
- Level
- Expert
- Locations
- 16
- Posted
- today
AlignerrApplied PhysicsPhysics · today Worldwide$40–$80/hrApply
About this role
You stress-test AI on physics topics such as quantum mechanics and thermodynamics. The work suits applicants with a PhD in physics.
What you'd do
- Red-team AI models
Requirements
- PhD
- Field: physics
Commitment
- Flexible schedule
Full description
- Platform
- Alignerr
- Pay rate
- $40–$80/hr
- Eligibility
- Worldwide
- Expertise
- Physics
- Level
- Expert
- Posted
- today
AlignerrPrincipal Cloud Security ArchitectSoftware & Coding · today Worldwide$40–$80/hrApply
About this role
The person works on cloud security, looking for weaknesses before attackers can exploit them. The role suits someone with advanced cloud security architecture experience.
What you'd do
- Red-team AI models
Full description
- Platform
- Alignerr
- Pay rate
- $40–$80/hr
- Eligibility
- Worldwide
- Expertise
- Software & Coding
- Level
- Expert
- Posted
- today
AlignerrAdversary Exploitation LeadSoftware & Coding · today Worldwide$40–$80/hrApply
About this role
The person analyzes real-world attack chains, exploit paths, and adversary tactics. The work suits someone with a background in cybersecurity or adversary analysis.
What you'd do
- Red-team AI models
Full description
- Platform
- Alignerr
- Pay rate
- $40–$80/hr
- Eligibility
- Worldwide
- Expertise
- Software & Coding
- Level
- Mid-level
- Posted
- today
AlignerrBackend Python DeveloperSoftware & Coding · today Worldwide$60–$90/hrApply
About this role
Review and challenge AI-generated Python code, focusing on backend development. The work suits someone with Python and software-development experience.
What you'd do
- Rate and critique AI answers
- Review code
- Red-team AI models
Full description
- Platform
- Alignerr
- Pay rate
- $60–$90/hr
- Eligibility
- Worldwide
- Expertise
- Software & Coding
- Level
- Mid-level
- Posted
- today
AlignerrOpenClaw Security Expert & Power UserSoftware & Coding · today Worldwide$15–$75/hrApply
About this role
The person probes and tests AI systems using security expertise, with the aim of finding weaknesses and helping harden them. The work suits someone with a security background and experience using AI systems.
What you'd do
- Red-team AI models
Requirements
- Security expertise
Commitment
- Flexible schedule
Full description
- Platform
- Alignerr
- Pay rate
- $15–$75/hr
- Eligibility
- Worldwide
- Expertise
- Software & Coding
- Level
- Mid-level
- Posted
- today
Showing 1-27 of 27 positions