AI Red Team Engineer - Italian

LILT is seeking AI Red Team experts to collaborate on adversarial testing of AI systems, specifically LLMs, multimodal models, RAG/embeddings, and product integrations. The role involves crafting prompts, exploring bypass methods, and documenting outcomes. It focuses on uncovering weaknesses and improving system defenses through collaborative research with engineers and safety researchers.

Requirements

  • Deep understanding of Generative AI and LLMs.
  • Cybersecurity and threat modeling experience.
  • Strong analytical skills and knowledge of NLP.
  • Commitment to ethical hacking and defensive security.

Benefits

  • Competitive rates
  • Part-time remote work
  • Access to advanced AI projects
  • Influence on future AI models
  • Professional development opportunities

Originally posted on Himalayas



source https://himalayas.app/companies/lilt/jobs/ai-red-team-engineer-italian