AI Red Teamer
2 weeks ago

Job summary
This role focuses on structured adversarial testing of language models. You will design and execute controlled test cases to identify vulnerabilities, edge cases, and systemic weaknesses in AI behavior.
Responsibilities
- Conduct structured adversarial testing of conversational AI systems
- Prompt injection scenarios
Job description
, consectetur adipiscing elit. Nullam tempor vestibulum ex, eget consequat quam pellentesque vel. Etiam congue sed elit nec elementum. Morbi diam metus, rutrum id eleifend ac, porta in lectus. Sed scelerisque a augue et ornare.
Donec lacinia nisi nec odio ultricies imperdiet.
Morbi a dolor dignissim, tristique enim et, semper lacus. Morbi laoreet sollicitudin justo eget eleifend. Donec felis augue, accumsan in dapibus a, mattis sed ligula.
Vestibulum at aliquet erat. Curabitur rhoncus urna vitae quam suscipit
, at pulvinar turpis lacinia. Mauris magna sem, dignissim finibus fermentum ac, placerat at ex. Pellentesque aliquet, lorem pulvinar mollis ornare, orci turpis fermentum urna, non ullamcorper ligula enim a ante. Duis dolor est, consectetur ut sapien lacinia, tempor condimentum purus.
Access all high-level positions and get the job of your dreams.
Similar jobs
Mercor connects elite creative and technical talent with leading AI research labs. We are looking for an AI Red Team Specialist to evaluate AI models by probing with adversarial inputs to surface vulnerabilities and enhance safety. · ...
5 days ago
Mercor connects elite creative and technical talent with leading AI research labs. · Red team conversational AI models and agents to identify jailbreaks, prompt injections, misuse cases, and bias exploitation. · Generate high-quality human data by annotating failures, classifying ...
1 month ago
Mercor connects elite creative and technical talent with leading AI research labs. Headquartered in San Francisco. · Red team conversational AI models and agents to identify jailbreaks, prompt injections, misuse cases, and bias exploitation. · Generate high-quality human data by ...
1 month ago
About 10a Labs: 10a Labs is the safety and threat-intelligence layer trusted by frontier AI labs, AI unicorns, Fortune 10 companies, and leading global technology platforms. Our adversarial red teaming model evaluations enable engineering teams to stay ahead of evolving threats. ...
3 days ago
About The Job · Mercor connects elite creative and technical talent with leading AI research labs. Headquartered in San Francisco. · Red team conversational AI models and agents by executing jailbreaks, prompt injections, and misuse cases. · ...
2 weeks ago
· The Cyber Event Red Teamer will provide direct support to the Plans and Exercise Lead for the Joint Cyber Training Enterprise. · ...
3 weeks ago
· The Cyber Event Red Teamer will provide direct support to the Plans and Exercise Lead for the Joint Cyber Training Enterprise, · Support the execution of cybersecurity training and testing events within cyber ranges. · Support the implementation of offensive based cyber range ...
6 days ago
The Cyber Event Red Teamer will provide direct support to the Plans and Exercise Lead for the Joint Cyber Training Enterprise.Cyber training and operations platform in a cyber range, · supporting the execution of cybersecurity training and testing events, · offensive based cyber ...
3 weeks ago
We have established a company culture that supports our employees, their families and the communities in which they live and work. · The Cyber Event Red Teamer will provide direct support to the Plans and Exercise Lead for the Joint Cyber Training Enterprise, · Support the execut ...
3 weeks ago
The Cyber Event Red Teamer will provide direct support to the Plans and Exercise Lead for the Joint Cyber Training Enterprise. · We are looking for an experienced Cyber Event Red Teamer to join our team at By Light Professional IT Services LLC. The candidate will support project ...
3 weeks ago
+The Cyber Event Red Teamer will provide direct support to the Plans and Exercise Lead for the Joint Cyber Training Enterprise. · +Support the execution of cybersecurity training and testing events within cyber ranges. · Support the implementation of offensive based cyber range c ...
2 weeks ago
Knight Federal Solutions is a trusted provider to industry leading prime contractors and the Department of Defense. · ...
3 weeks ago
The Cyber Event Red Teamer will provide direct support to the Plans and Exercise Lead for the Joint Cyber Training Enterprise. · Support the execution of cybersecurity training and testing events within cyber ranges. · Support the implementation of offensive based cyber range con ...
2 weeks ago
This project involves reviewing AI outputs on sensitive topics like bias and misinformation. · All work is text-based, and participation in higher-sensitivity projects is optional.Prior red teaming experience in AI adversarial work or cybersecurity. · Curious and adversarial mind ...
1 month ago
We are seeking an experienced Human Redteamer to conduct redteaming for AI models. · We will provide a chat style interface that you will interact with to identify vulnerabilities and behavioral weaknesses in the model. · Must have knowledge of red teaming methodologiesPrior redt ...
1 month ago
Position: AI Red-Teamer — Adversarial AI Testing (Novice) · ...
1 month ago
We're building a pod of AI Red-Teamers: human data experts who probe AI models with adversarial inputs, surface vulnerabilities and generate the red-team data that makes AI safer for our customers. · Red-team AI models and agents: jailbreaks, prompt injections, misuse cases, expl ...
3 weeks ago
+Job summary · We are seeking an experienced Human Redteamer to conduct output redteaming via Playground for our Language Learning Model (LLM).++ engage in systematic testing to identify vulnerabilities and behavioral weaknesses in the model. · Your insights will play a crucial r ...
1 week ago
Mercor connects elite creative and technical talent with leading AI research labs. · About The Job · Mercor connects elite creative and technical talent with leading AI research labs. · ...
1 month ago
AI Red-Teamer (Adversarial AI Testing) | 111/hr Remote
Only for registered members
We are seeking an experienced AI Red-Teamer to conduct advanced adversarial testing of AI models and agents. The ideal candidate will have prior experience in AI red-teaming, adversarial AI testing, cybersecurity, or socio-technical risk analysis. · ...
1 month ago