AI Safety Expert, English, Finnish

Weekday (YC W21)

. Red team conversational AI models and agents using jailbreaks, prompt injections, misuse cases, bias exploitation, and multi-turn manipulation .

Posted 9/17/2026contractRemote • United StatesMid-LevelSenior💰 $48 - $62 per hourWebsite

Core Competencies

Role fit

Core Competencies

Use this summary to align your resume positioning with the role.

Demonstrates expertise in red teaming AI systems through adversarial probing techniques, including jailbreaks and prompt injections, while effectively generating human data and producing reproducible reports. Proficient in communicating risks to diverse stakeholders and adapting methodologies across various projects.

Highest-signal resume keywords

Red Teaming ExperienceAdversarial ProbingFluent in English and FinnishReport ProductionVulnerability Classification

ATS Keywords

Tailor your resume

Applicant Tracking System Keywords

Tip: use these terms in your resume and cover letter to boost ATS matches.

Hard Skills

JailbreaksPrompt InjectionsMisuse CasesBias ExploitationMulti-Turn ManipulationData AnnotationSystemic Risk FlaggingTaxonomiesBenchmarksPlaybooks

Soft Skills

Clear CommunicationAdaptability

Industry Keywords

AI Adversarial WorkCybersecuritySocio-Technical Probing

Tech Stack

Tools & technologies

Cyber Security

About the role

Key responsibilities & impact

Red team conversational AI models and agents using jailbreaks, prompt injections, misuse cases, bias exploitation, and multi-turn manipulation
Generate human data by annotating failures, classifying vulnerabilities, and flagging systemic risks
Follow taxonomies, benchmarks, and playbooks to keep testing consistent
Produce reproducible reports, datasets, and attack cases for customers
Uncover vulnerabilities automated tests miss
Deliver reproducible artifacts that strengthen customer AI systems
Expand evaluation coverage by testing more scenarios and reducing production surprises

Requirements

What you’ll need

Fluent/native fluency in English and Finnish
Prior red teaming experience in AI adversarial work, cybersecurity, or socio-technical probing
Ability to probe AI systems adversarially, including jailbreaks, prompt injections, misuse cases, bias exploitation, and multi-turn manipulation
Ability to generate human data by annotating failures, classifying vulnerabilities, and flagging systemic risks
Ability to follow taxonomies, benchmarks, and playbooks
Ability to produce reproducible reports, datasets, and attack cases
Ability to explain risks clearly to technical and non-technical stakeholders
Ability to adapt across projects and customers

Benefits

Comp & perks

Participation in higher-sensitivity projects is optional
Clear guidelines for sensitive-content work
Wellness resources