AI Adversarial Specialist (Remote)

About the role

We are looking for an AI Adversarial Specialist to join our remote team and help secure conversational AI models. You will work independently to uncover jailbreaks, prompt injections, bias exploits and other vulnerabilities, ensuring our clients receive robust safety assessments.

Key responsibilities

• 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 vulnerabilities and flagging systemic risks.
• Apply structured taxonomies, benchmarks and playbooks to guarantee consistent testing across projects.
• Document findings reproducibly and produce reports, datasets and actionable attack cases for customers.
• Collaborate asynchronously with stakeholders while meeting deadlines and improving model performance.

Required profile

• Fluent in English and Finnish.
• Prior experience in red‑team, AI adversarial work, cybersecurity or socio‑technical probing.
• Ability to communicate technical risks clearly to both technical and non‑technical audiences.

Required skills

• Adversarial Machine Learning
• Prompt Injection techniques
• Model Extraction
• Penetration testing
• Exploit development

What we offer

• Fully remote contract position.
• Competitive hourly rate of $48–$62.
• Opportunity to work with leading AI research labs and improve AI safety.