Research Engineer - AI Safety Systems and Guardrails

Analisi del mercato

Gratis, dopo l'accesso.

Candidati

Carica il tuo CV: datori di lavoro e recruiter di diversi paesi che cercano il tuo profilo potranno contattarti direttamente.

Descrizione

We are seeking an experienced Research Engineer to join the System Safety team within Product & Applied Research org at Meta Superintelligence Labs. This role will focus on researching and developing advanced machine learning models, novel algorithms, and scalable systems that improve the safety of Meta's AI products, including Meta AI and conversational, multimodal, and agentic experiences. You will bring current AI safety research into practical product safeguards, with a primary focus on guardrails, policy-adaptable risk detection, adversarial robustness, and safe agent behavior. This is a hands-on technical leadership role with end-to-end ownership of a significant safety area—from setting research direction and developing methods through rigorous evaluation, cross-team integration, and continuous improvement in production. Research and develop state-of-the-art machine learning models and novel algorithms for AI safety, with a primary focus on guardrails, risk detection, policy adherence, and adversarial robustness Design, prototype, and implement safety systems for language models, multimodal models, and AI agents, addressing harmful assistance, jailbreaks, prompt injection, unsafe tool use, and unauthorized information disclosure across individual interactions and complete agent tasks Set the technical direction and research roadmap for a significant system safety area, leading complex initiatives across research, alignment, evaluation, product, and infrastructure teams

Descrizione completa, azienda e link per candidarti: dopo l'accesso. Accedi

I contatti del datore di lavoro (email/telefono/telegram) sono nascosti nell'anteprima pubblica. Invia il tuo CV così i datori di lavoro possono contattarti direttamente.