02 ott - Padova
Mercor
ph3About the job /h3 pMercor connects elite creative and technical talent with leading AI research labs. Headquartered in San Francisco, our investors include bBenchmark /b, bGeneral Catalyst /b, bPeter Thiel /b, bAdam D'Angelo /b, bLarry Summers /b, and bJack Dorsey /b. /p pbPosition: /b AI Safety Red Teamerbr/bType: /b bContract /bbr/bCompensation: /b b$70–$84/hour /bbr/bLocation: /b bRemote /b /p h3Role Responsibilities /h3 ul liDesign adversarial prompts to stress-test frontier bAI models /b. /li liIdentify jailbreaks, unsafe behaviors, hallucinations, and policy failures. /li liEvaluate model robustness across misinformation, cyber, biosecurity, fraud, political content, and other sensitive domains. /li liDocument vulnerabilities and contribute to safety benchmarking and red-teaming reports. /li liCollaborate with bAI researchers /b to improve model alignment, robustness, and safety. /li /ul h3Qualifications /h3 h3Must-Have /h3 ul libBachelor's degree /b or higher in bComputer Science /b, bCybersecurity /b, bJournalism /b,
bCommunications /b, bPsychology /b, bBiology /b, bChemistry /b, bPublic Policy /b, or a related discipline. /li lib5+ years /b of professional experience in bAI Safety /b, bAI Red Teaming /b, bTrust Safety /b, cybersecurity, investigative journalism, life sciences, or a related field. /li liStrong analytical reasoning, prompt design, and written communication skills. /li liExperience designing adversarial prompts or evaluating frontier bAI systems /b. /li /ul h3Preferred /h3 ul liExperience with bAI Red Teaming /b, bRLHF /b, bSFT /b, bAI Alignment /b, or bTrust Safety /b. /li liFamiliarity with jailbreak testing, prompt engineering, or adversarial evaluation methodologies. /li liExpertise in one or more grey-area domains, including cyber, biosecurity, political content, misinformation, or scientific safety. /li /ul /p #J-*****-Ljbffr
05 ott - Milano
ACCA Careers
05 ott - Tortona
LOGICAL JOB
05 ott - Cassino
supernova
05 ott - Calderara di Reno
Risorse