AI Safety Red Teaming Expert in English and Swedish

About OpenTrain

OpenTrain AI is the hiring and contracting organization for this role and the #1 platform for finding and building careers in AI training and data labeling. OpenTrain helps contributors discover meaningful AI work, build a professional profile, and apply in minutes. Creating an OpenTrain account is free.

About AI Safety Training

AI training is the human side of building artificial intelligence. Specialists test and evaluate model behavior, label failures, and provide structured feedback that helps AI systems become more useful and safer. Red teaming is a high-impact form of this work, using adversarial testing to uncover weaknesses before they affect users.

The Role

OpenTrain AI is hiring an AI Safety Red Teaming Expert fluent in English and Swedish. You will probe conversational AI models and agents with adversarial inputs, generate critical safety data, and document vulnerabilities in reproducible reports. This is a remote, text-based contractor role focused on cutting-edge AI safety testing.

• Contractor position
• Part-time engagement
• Worldwide remote opportunity
• 20+ hours per week
• Pay: $48 to $62 per hour, with a listed rate of $62 per hour
• Languages: native English and Swedish fluency
• Experience level: entry level

What You'll Do

You will conduct structured adversarial testing and turn your findings into high-quality data that can guide improvements to conversational AI systems. Your work will combine creative probing with consistent evaluation, classification, and documentation.

• Red team conversational AI models and agents with jailbreaks, prompt injections, and multi-turn manipulation.
• Generate human data by annotating failures, classifying vulnerabilities, and flagging systemic risks.
• Follow structured taxonomies, benchmarks, and playbooks to keep testing consistent.
• Document every test reproducibly.
• Produce reports, datasets, and attack cases that customers can act on directly.

Required Skills

This role calls for an experienced adversarial thinker who can test systems methodically and communicate findings clearly. You should be comfortable moving between creative attack design, structured frameworks, and practical risk reporting.

• Prior red teaming experience in AI adversarial work, cybersecurity, or socio-technical probing.
• A curious and adversarial mindset that instinctively pushes systems to their breaking points.
• A structured approach using frameworks or benchmarks rather than random testing.
• Strong communication skills for explaining risks to technical and non-technical stakeholders.
• Adaptability when moving across projects and customers.
• Native fluency in English and Swedish.

Helpful Background

Additional experience in any of the following areas can support your work on AI safety testing projects:

• Adversarial machine learning, including jailbreak datasets, prompt injection, RLHF or DPO attacks, and model extraction.
• Cybersecurity, including penetration testing, exploit development, or reverse engineering.
• Socio-technical risk work, such as harassment or disinformation probing, abuse analysis, or conversational AI testing.
• Creative probing through psychology, acting, or writing for unconventional adversarial thinking.

Why This Work Matters

Modern AI systems depend on people who can identify unsafe behavior, evaluate model outputs, and prepare reliable training data. By exposing vulnerabilities and describing them precisely, you will contribute directly to the development of safer AI systems while working remotely in a fast-growing technical field.

• Work at the frontier of AI safety and conversational model evaluation.
• Use English and Swedish language expertise in adversarial testing.
• Build experience in AI training, safety evaluation, and structured data production.
• Work remotely with a flexible part-time schedule of 20+ hours per week.

Apply Through OpenTrain

Create a free OpenTrain account to build your AI training profile and apply for this contractor opportunity. OpenTrain brings together projects across the AI training industry so contributors can find work and grow their careers in one place.

• Review the role requirements and supported languages.
• Highlight relevant AI red teaming, cybersecurity, socio-technical, or creative probing experience.
• Apply through OpenTrain for consideration.