This is a fully remote position, open to applicants in United States.

📋 Description

• Engage in red team activities with conversational AI models and agents utilizing jailbreaks, prompt injections, misuse scenarios, bias exploitation, and multi-turn manipulation.

• Create human data by annotating failures, categorizing vulnerabilities, and identifying systemic risks.

• Adhere to taxonomies, benchmarks, and playbooks to ensure consistent testing procedures.

• Generate reproducible reports, datasets, and attack cases for clients.

• Identify vulnerabilities that automated tests may overlook.

• Deliver reproducible artifacts that enhance the robustness of customer AI systems.

• Broaden evaluation coverage by testing additional scenarios and minimizing production surprises.

⛳️ Requirements

• Proficient/native fluency in both English and Finnish.

• Previous experience in red teaming within AI adversarial contexts, cybersecurity, or socio-technical probing.

• Capability to probe AI systems adversarially, including the use of jailbreaks, prompt injections, misuse cases, bias exploitation, and multi-turn manipulation.

• Skill in generating human data through failure annotation, vulnerability classification, and systemic risk identification.

• Ability to adhere to taxonomies, benchmarks, and playbooks.

• Expertise in producing reproducible reports, datasets, and attack cases.

• Proficiency in clearly communicating risks to both technical and non-technical stakeholders.

• Flexibility to adapt across various projects and customer requirements.