Finnish Bilingual AI Safety Red Team Expert

About OpenTrain

OpenTrain AI is the hiring and contracting organization for this role. OpenTrain is the #1 platform for finding and building careers in AI training and data labeling, helping specialists discover projects, build a professional profile, and apply in minutes.

Creating an OpenTrain account is free, and your profile can help you present credible AI training experience while finding work aligned with your expertise.

• Remote contract opportunity
• Work with a fast-growing AI training organization
• Build a lasting portfolio in AI safety and model evaluation

About AI Safety Red Teaming

AI training is the human side of building artificial intelligence. People test, review, classify, and improve model behavior so that modern AI systems become more useful, reliable, and safer.

Red teaming applies adversarial thinking to conversational AI models and agents. By uncovering failures that automated testing can miss, human experts provide structured evidence that technical teams can use to improve system behavior.

• Probe AI systems with adversarial inputs
• Turn model failures into structured human data
• Help identify risks before they affect real users

The Role

OpenTrain is recruiting an expert Finnish bilingual AI safety red team specialist to test conversational AI models and agents. You will investigate jailbreaks, prompt injections, misuse cases, bias exploitation, and multi-turn manipulation, then document findings in a clear and reproducible format.

This text-based work may involve sensitive topics such as bias, misinformation, or harmful behaviors. Participation in higher-sensitivity projects is optional and supported by clear topic guidance and wellness resources.

• Experience level: Expert
• Native fluency in Finnish and English required
• Remote contract role
• Pay: $48 to $62 per hour

What You'll Do

You will combine creative adversarial thinking with structured evaluation methods. Your findings will help expand safety coverage and give technical teams actionable attack cases, datasets, and reports.

• Test conversational AI models and agents against adversarial scenarios
• Identify jailbreaks, prompt injections, misuse cases, and bias exploitation
• Annotate model failures and classify vulnerabilities
• Identify systemic risks and apply relevant taxonomies
• Use benchmarks and structured testing playbooks consistently
• Produce reproducible reports, datasets, and attack cases
• Uncover vulnerabilities that automated tests may miss
• Communicate security and safety risks clearly to technical and non-technical audiences

Required Qualifications

This is an expert-level opportunity for someone with prior AI adversarial red teaming, cybersecurity, or socio-technical probing experience. You should be comfortable working creatively while maintaining disciplined documentation and classification practices.

• Prior AI adversarial red teaming or cybersecurity experience
• Ability to identify jailbreaks, prompt injections, misuse cases, and bias exploitation
• Experience applying taxonomies, benchmarks, or structured testing playbooks
• Ability to classify vulnerabilities and communicate systemic risks clearly
• Ability to document findings reproducibly
• Native fluency in both Finnish and English
• Curiosity, adaptability, and sound judgment when probing systems creatively

Helpful Background

The following experience may be especially relevant to this work. These backgrounds can support unconventional adversarial thinking, technical investigation, or analysis of how people and systems behave under pressure.

• Adversarial machine learning
• Jailbreak or prompt injection testing
• Penetration testing
• Exploit development
• Reverse engineering
• Abuse analysis
• Conversational AI testing
• Psychology
• Acting
• Writing that supports unconventional adversarial thinking

Schedule and Compensation

This is a remote contract opportunity with a default commitment of 40 hours per week. The listed time requirement is 20+ hours per week, and the compensation range is $48 to $62 per hour.

• Employment type: Contractor and part-time
• Default weekly commitment: 40 hours
• Listed time requirement: 20+ hours per week
• Hourly compensation: $48 to $62 USD

How to Apply Through OpenTrain

Create a free OpenTrain account, build your profile around your AI safety and red teaming experience, and apply through OpenTrain. Your profile gives you one place to present relevant expertise, discover matching opportunities, and develop a long-term career portfolio in AI training.

• Create a free OpenTrain account
• Highlight Finnish and English fluency and red teaming experience
• Showcase structured testing, vulnerability classification, and reporting skills
• Apply in minutes through OpenTrain