ActiveFence
ActiveFence
ActiveFence este o companie de securitate cibernetică și inteligență artificială axată pe încredere și siguranță pentru platformele online. Oferta sa completă combină cercetarea de informații, detectarea conținutului dăunător cu ajutorul inteligenței artificiale și instrumente de moderare a conținutului, ajutând platformele să gestioneze riscuri precum exploatarea copiilor, dezinformarea, discursul instigator la ură, terorismul, nuditatea, frauda și alte forme de abuz online. ActiveFence sprijină echipele de încredere și siguranță de diferite dimensiuni, contribuind la protejarea a peste trei miliarde de utilizatori din întreaga lume, în mai mult de 100 de limbi.

AI Red Team – GenAI Adversarial Evaluation at ActiveFence

Develop adversarial attacks, datasets, and benchmarks for ActiveFence’s AI security platform. Test LLM robustness through red teaming and vulnerability research.

Descriere

  • Design new adversarial attacks.
  • Help build scalable systems for generating and testing attacks at scale.
  • Assess attacks for quality, effectiveness, novelty, and reproducibility.
  • Discover emerging attack patterns and model vulnerabilities.
  • Create adversarial datasets, benchmarks, and regression tests.
  • Share findings, methods, and structured attack data with Data Science, Security, and Engineering teams.
  • Contribute to stronger model robustness and defenses.

Cerințe

  • At least three years of professional experience in cybersecurity, security research, red teaming, or a related security field.
  • Bachelor’s degree in Data Science, Computer Engineering, Computer Science, or a closely related technical field.
  • Strong knowledge of large language models, prompt injection, and AI security.
  • Experience in red teaming, security research, or adversarial testing.
  • Strong Python and automation skills.
  • Creative problem-solving skills and the ability to develop new attack techniques.
  • Ability to analyze results and communicate findings clearly.
  • Offensive cybersecurity certifications such as OSWA, OSWE, OSCE3, SEC542, or SEC522 are preferred.

Locuri de muncă similare

Kreato Global | BPO and Language Solutions

Remote English-Spanish OPI/VRI Interpreter

Kreato Global | BPO and Language Solutions

Interpret remotely between English- and Spanish-speaking people in medical, financial, social service, and customer care settings. Provide language support for Kreato Global across Latin America.

Deschide
RecruitGo

Remote Executive Assistant, Outreach and Marketing — Philippines

RecruitGo

Handle administrative support, CRM, outreach, and marketing for RecruitGo, an Employer of Record serving global clients with talent from emerging markets. Support two UK-facing clients with day-to-day administration and creative campaigns.

Deschide