AI
Reasoning
Mathematics
+11
Writing
Red Teaming
Engineering
Testing
Analysis
Training
Make
Research
Vulnerability Assessment
Performance Testing
Technical Writing
Mercor is assembling a panel of nuclear materials and safeguards experts to red-team frontier AI models. The goal is to test whether a model can correctly judge the misuse potential of a technical request — answering legitimate questions fully while refusing genuinely dangerous…
AI
Reasoning
Mathematics
+12
Engineering
Writing
Red Teaming
Operations
Management
Analysis
Economics
Licensing
Make
Research
Process Design
Systems Analysis
Mercor is assembling a panel of nuclear materials and safeguards experts to red-team frontier AI models. The goal is to test whether a model can correctly judge the misuse potential of a technical request — answering legitimate questions fully while refusing genuinely dangerous…
AI
Reasoning
Mathematics
+12
Writing
Red Teaming
Planning
Verification
Reporting
Analysis
Instrumentation
Monitoring
Make
Research
Policy analysis
Technical Writing
Mercor is assembling a panel of nuclear materials and safeguards experts to red-team frontier AI models. The goal is to test whether a model can correctly judge the misuse potential of a technical request — answering legitimate questions fully while refusing genuinely dangerous…
Medicine
AI
Reasoning
+8
Mathematics
Go
Writing
Red Teaming
Operations
Make
Research
Technical Writing
Mercor is assembling a panel of radiological safety experts to red-team frontier AI models. The goal is to test whether a model can correctly judge the misuse potential of a technical request — answering legitimate questions fully while refusing genuinely dangerous ones.
AI
Reasoning
Mathematics
+10
Writing
Red Teaming
Planning
Monitoring
Microsoft Teams
Public Health
Triage
Make
Research
Technical Writing
Mercor is assembling a panel of radiological safety experts to red-team frontier AI models. The goal is to test whether a model can correctly judge the misuse potential of a technical request — answering legitimate questions fully while refusing genuinely dangerous ones.
AI
Reasoning
Mathematics
+7
Writing
Red Teaming
Compliance
Make
Research
Vulnerability Assessment
Technical Writing
Mercor is assembling a panel of radiological safety experts to red-team frontier AI models. The goal is to test whether a model can correctly judge the misuse potential of a technical request — answering legitimate questions fully while refusing genuinely dangerous ones.
AI
Reasoning
Mathematics
+9
Planning
Writing
Red Teaming
Physics
Verification
Operations
Make
Research
Technical Writing
Mercor is assembling a panel of radiological safety experts to red-team frontier AI models. The goal is to test whether a model can correctly judge the misuse potential of a technical request — answering legitimate questions fully while refusing genuinely dangerous ones.
AI
Reasoning
Mathematics
+12
Writing
Red Teaming
Management
Compliance
Research
Licensing
Training
Reporting
Make
Radiation Safety
Project Management
Regulatory Compliance
Mercor is assembling a panel of radiological safety experts to red-team frontier AI models. The goal is to test whether a model can correctly judge the misuse potential of a technical request — answering legitimate questions fully while refusing genuinely dangerous ones.
AI
Cybersecurity
Flexible
+12
Institutions
History
Infrastructure
Training
Communication
LLMs
Engineering
Testing
Combine
Research
Operations
Rubrics
Please note: We are not currently hiring candidates based in California for this role. Cybersecurity Red Teamer Location: Seattle, WA, or Remote within the United States Work arrangement: Flexible, including part-time availability Handshake was founded on a simple belief:…
AI
Institutions
History
+12
Infrastructure
Training
Testing
FAR
Accuracy
Rubrics
Reasoning
Literature
Microsoft Teams
Education
Chemistry
Biochemistry
Please note: We are not currently hiring candidates based in California for this role. About Handshake Handshake was founded on a simple belief that everyone deserves a path to a great career, regardless of where they went to school or who they know.
Red Teaming
Assurance
Consistency
+12
AI
Safety Evaluation
Quality Assurance
Reasoning
Alignment
Formatting
Instruction Following
Rubrics
Onboarding
Documentation
English
Communication
In this hourly, remote contractor role, you will work as a Red-Teaming Quality Assurance Lead (QAL) to oversee quality, consistency, and trainer performance across AI red-teaming and safety-evaluation projects.
GenAI
Research
AI
+12
Testing
Communication
Leadership
Collaboration
Microsoft Teams
Operations
English
Ethics
Benchmarking
Red Teaming
Generative AI
Adversarial Testing
Alice is seeking an experienced and detail-oriented GenAI Safety Team Lead to oversee complex research and delivery efforts focused on identifying and mitigating risks in Generative AI systems.
AI
Go
GenAI
+12
Accuracy
Biology
Genetics
Chemistry
Virology
Epidemiology
Immunology
Compliance
Research
Communication
Red Teaming
Consulting
Alice.io (formerly known as ActiveFence) is a leading trust, safety, and security company. Just like 'Alice' herself, we go down the rabbit hole into the emerging world of AI and focus on safeguarding these technologies.
AI
Go
Analysis
+12
Testing
Infrastructure
Microsoft Teams
Research
Documentation
Reporting
Management
Problem Solving
Communication
Python
Node.js
Cybersecurity
Alice.io (formerly known as ActiveFence) is a leading trust, safety, and security company. Just like ‘Alice’ herself, we go down the rabbit hole into the emerging world of AI and focus on safeguarding these technologies.
You'll systematically probe large language models to find inputs that cause them to bypass safety guidelines and produce harmful, disallowed, or policy-violating outputs.
AI
Testing
Microsoft Teams
+12
Engineering
Documentation
Communication
Cross-Functional Collaboration
Cybersecurity
Research
Open Source
Jailbreaking
AI Safety
Red Teaming
Large Language Models
Language Models
Role Title: AI Safety & Red Teaming Specialist Role Type: Contractor Location: Remote We are looking for an experienced AI Safety & Red Teaming Specialist to help evaluate and strengthen the safety, security, and robustness of next-generation AI systems.
HireArt is recruiting AI Red Teaming Generalists on behalf of a global leader in AI development. In this role, you will help train and evaluate generative AI systems to ensure they produce safe, accurate, and responsible outputs.
AI
Cybersecurity
Testing
+12
Machine Learning
Journalism
Writing
Onboarding
Reporting
Slack
Engineering
Research
Analysis
Safety Evaluation
Penetration Testing
Creative Writing
We need people who can think like attackers. You will methodically test AI models against a taxonomy of failure modes: harmful content generation, jailbreak susceptibility, PII leakage, bias amplification, and more.
AI
Writing
Infrastructure
+12
Creativity
Cybersecurity
Testing
Machine Learning
Journalism
Engineering
Research
Analysis
Onboarding
AI Safety
Language Models
Network Infrastructure
This role is adversarial by design. You will probe language models for weaknesses by writing creative, unusual, and sometimes uncomfortable prompts designed to surface failure modes.
AI
Cybersecurity
Testing
+12
Machine Learning
Journalism
Writing
Communication
Reporting
Documentation
Engineering
Onboarding
Penetration Testing
Creative Writing
Written communication
AI Safety
We need people who can think like attackers. You will methodically test AI models against a taxonomy of failure modes: harmful content generation, jailbreak susceptibility, PII leakage, bias amplification, and more.
AI
Combine
Engineering
+12
Research
Literature
Writing
Journalism
Cybersecurity
Testing
Machine Learning
Onboarding
Analysis
AI Safety
Prompt Engineering
Security Research
We need people who can think like attackers. You will methodically test AI models against a taxonomy of failure modes: harmful content generation, jailbreak susceptibility, PII leakage, bias amplification, and more.
