Job DescriptionJob Description
About the job
n
Mercor connects elite creative and technical talent with leading AI research labs. Headquartered in San Francisco, our investors include Benchmark, General Catalyst, Peter Thiel, Adam D'Angelo, Larry Summers, and Jack Dorsey.
n
Position: AI Safety Experts — English & Bengali
nType: Contract
nCompensation: $16–$22/hour
nLocation: Remote
n
Role Responsibilities
n
nRed team conversational AI models and agents. Conduct jailbreaks, prompt injections, misuse cases, and bias exploitation.nGenerate high-quality human data. Annotate failures, classify vulnerabilities, and flag systemic risks.nApply structure. Follow taxonomies, benchmarks, and playbooks to keep testing consistent.nDocument reproducibly. Produce reports, datasets, and attack cases customers can act on.nWork independently and asynchronously. Thrive in flexible hours while improving AI model performance.nn
Qualifications
n
Must-Have
n
nNative fluency in English and Bengali.nStrong judgment about language and content.nRigorous attention to detail and structure.nExcellent communication skills for technical and non-technical audiences.nAdaptability across projects, task types, and customers.nn
Preferred
n
nExperience in Adversarial ML: jailbreak datasets, prompt injection, RLHF/DPO attacks, model extraction.nBackground in Cybersecurity: penetration testing, exploit development, reverse engineering.nKnowledge of socio-technical risk: harassment/disinfo probing, abuse analysis, conversational AI testing.nCreative probing skills: psychology, acting, writing for unconventional adversarial thinking.nn
Application Process (Takes 20–30 mins to complete)
n
nUpload resumenAI interview based on your resumenSubmit formnn
Resources & Support
n
nFor details about the interview process and platform information, please check: https://talent.docs.mercor.com/welcomenFor any help or support, reach out to:
[email protected]
PS: Our team reviews applications daily. Please complete your AI interview and application steps to be considered for this prospect.
📌 AI Safety Expert - Adversarial ML (Canada)
🏢 Default Project
📍 Canada