AI Red-Teamer - Adversarial AI Testing English
Top Benefits
About the role
This role is for one of our clients
Compensation: $50-$111 per hourWe are seekingAI Red-Teamersto help test and strengthen modern AI systems through adversarial evaluation. In this role, you will challenge AI models with carefully designed inputs to uncover weaknesses, surface vulnerabilities, and generate high-quality data that improves the safety, reliability, and robustness of conversational AI.
This work focuses on proactively identifying potential risks before they appear in real-world use. By systematically probing AI systems, you will help ensure they respond safely, accurately, and responsibly across a wide range of scenarios.
This role may include reviewing AI outputs that referencesensitive topics such as bias, misinformation, or harmful behaviors. All work is text-based, and participation in higher-sensitivity projects is optional and supported with clear guidelines and wellness resources.
Requirements
What You’ll Do
-Red-team AI models and agentsby testing jailbreak attempts, prompt injections, misuse scenarios, and exploit strategies -Generate high-quality human evaluation databy annotating model failures, classifying vulnerabilities, and identifying systemic risks -Apply structured testing methodologiesusing taxonomies, benchmarks, and playbooks to ensure consistent evaluation -Document findings clearly and reproducibly, producing reports, datasets, and adversarial test cases that teams can act upon -Work across multiple projects, supporting different AI systems and evaluation objectives
Who You Are
- You haveprior red-teaming experience, such as adversarial AI testing, cybersecurity, or socio-technical risk analysis
- You naturally thinkadversarially, exploring ways to push systems to their limits and uncover weaknesses
- You preferstructured methodologies, using frameworks and benchmarks rather than ad-hoc testing
- You communicate risks and vulnerabilitiesclearly to both technical and non-technical audiences
- You are comfortableworking across multiple projects and adapting to new evaluation challenges
Nice-to-Have Specialties
-**Adversarial Machine Learning:**jailbreak datasets, prompt injection attacks, RLHF/DPO vulnerabilities, or model extraction techniques -**Cybersecurity:**penetration testing, exploit development, reverse engineering -**Socio-technical risk analysis:**harassment or misinformation testing, abuse pattern analysis -**Creative adversarial thinking:**backgrounds in psychology, acting, writing, or other disciplines that support unconventional attack strategies
What Success Looks Like
- You uncover vulnerabilities and failure modes that automated tests miss
- Your work producesreproducible artifacts and datasetsthat improve AI system resilience
- Evaluation coverage expands withmore realistic adversarial scenarios tested before deployment
- AI systems becomesafer and more reliabledue to your rigorous testing and insights
Why Join
- Contribute directly tofrontier work in AI safety and adversarial testing
- Help improve therobustness, safety, and trustworthiness of modern AI systems
- Gain hands-on experience working withhuman data-driven AI evaluation methodologies
Compensation may vary depending on theproject, customer requirements, level of expertise, and content sensitivityinvolved in each engagement.
Contract and Payment Terms
- Engagement will be as anindependent contractor
- This is afully remote rolethat can be completed on your own schedule
- Projects may beextended, shortened, or concluded earlydepending on project needs and performance
- Work performed willnot involve access to confidential or proprietary informationfrom any employer, client, or institution -Payments are issued weeklyviaStripe or Wisebased on services rendered
Please note:Candidates requiring H1-B or STEM OPT sponsorship cannot be supported for this role at this time.
About Weekday AI
Similar jobs you might like
AI Red-Teamer - Adversarial AI Testing English
Top Benefits
About the role
This role is for one of our clients
Compensation: $50-$111 per hourWe are seekingAI Red-Teamersto help test and strengthen modern AI systems through adversarial evaluation. In this role, you will challenge AI models with carefully designed inputs to uncover weaknesses, surface vulnerabilities, and generate high-quality data that improves the safety, reliability, and robustness of conversational AI.
This work focuses on proactively identifying potential risks before they appear in real-world use. By systematically probing AI systems, you will help ensure they respond safely, accurately, and responsibly across a wide range of scenarios.
This role may include reviewing AI outputs that referencesensitive topics such as bias, misinformation, or harmful behaviors. All work is text-based, and participation in higher-sensitivity projects is optional and supported with clear guidelines and wellness resources.
Requirements
What You’ll Do
-Red-team AI models and agentsby testing jailbreak attempts, prompt injections, misuse scenarios, and exploit strategies -Generate high-quality human evaluation databy annotating model failures, classifying vulnerabilities, and identifying systemic risks -Apply structured testing methodologiesusing taxonomies, benchmarks, and playbooks to ensure consistent evaluation -Document findings clearly and reproducibly, producing reports, datasets, and adversarial test cases that teams can act upon -Work across multiple projects, supporting different AI systems and evaluation objectives
Who You Are
- You haveprior red-teaming experience, such as adversarial AI testing, cybersecurity, or socio-technical risk analysis
- You naturally thinkadversarially, exploring ways to push systems to their limits and uncover weaknesses
- You preferstructured methodologies, using frameworks and benchmarks rather than ad-hoc testing
- You communicate risks and vulnerabilitiesclearly to both technical and non-technical audiences
- You are comfortableworking across multiple projects and adapting to new evaluation challenges
Nice-to-Have Specialties
-**Adversarial Machine Learning:**jailbreak datasets, prompt injection attacks, RLHF/DPO vulnerabilities, or model extraction techniques -**Cybersecurity:**penetration testing, exploit development, reverse engineering -**Socio-technical risk analysis:**harassment or misinformation testing, abuse pattern analysis -**Creative adversarial thinking:**backgrounds in psychology, acting, writing, or other disciplines that support unconventional attack strategies
What Success Looks Like
- You uncover vulnerabilities and failure modes that automated tests miss
- Your work producesreproducible artifacts and datasetsthat improve AI system resilience
- Evaluation coverage expands withmore realistic adversarial scenarios tested before deployment
- AI systems becomesafer and more reliabledue to your rigorous testing and insights
Why Join
- Contribute directly tofrontier work in AI safety and adversarial testing
- Help improve therobustness, safety, and trustworthiness of modern AI systems
- Gain hands-on experience working withhuman data-driven AI evaluation methodologies
Compensation may vary depending on theproject, customer requirements, level of expertise, and content sensitivityinvolved in each engagement.
Contract and Payment Terms
- Engagement will be as anindependent contractor
- This is afully remote rolethat can be completed on your own schedule
- Projects may beextended, shortened, or concluded earlydepending on project needs and performance
- Work performed willnot involve access to confidential or proprietary informationfrom any employer, client, or institution -Payments are issued weeklyviaStripe or Wisebased on services rendered
Please note:Candidates requiring H1-B or STEM OPT sponsorship cannot be supported for this role at this time.