AI Red Team Engineer — LLM

Be at the forefront of AI security research, specifically focused on protecting AI systems in financial services. You’ll discover vulnerabilities in AI models, design defenses, and help establish NexusAI as the thought leader in secure AI for payments.

• 
  
• Define a new field (AI security in payments)
  
• Do offensive security on cutting‑edge AI systems
  
• Publish research that shapes the industry
  
• Protect billions in transactions from AI‑specific attacks
  

• 
  
• Conduct adversarial attacks on our LLMs and fraud models
  
• Test for prompt injection, jailbreaking, model extraction
  
• Simulate real‑world attack scenarios (fraudsters manipulating AI)
  
• Document vulnerabilities and work with engineering to fix
  
• Perform quarterly security assessments for customers
  

• 
  
• Research novel AI attack vectors in payment systems
  
• Develop defensive techniques (adversarial training, input validation, output filtering)
  
• Build tools for automated AI security testing
  
• Stay current on AI security research (papers, conferences, threat intelligence)
  
• Contribute to open source AI security projects
  

• 
  
• Publish research findings (blog posts, white papers, academic papers)
  
• Present at security conferences
  
• Contribute to AI security standards and frameworks
  
• Build Moofwd reputation as AI security expert
  
• Engage with security community (Social media)
  

• 
  
• Present red‑team findings to customer CISOs
  
• Provide AI security guidance and best practices
  
• Support sales process with technical credibility
  
• Deliver training on AI security to customer teams
  

• 
  
• 3+ years in security research or offensive security
  
• Deep understanding of ML/AI systems (architectures, training, inference)
  
• Hands‑on experience with adversarial ML or AI security
  
• Strong Python skills + ML frameworks (PyTorch, TensorFlow)
  
• Experience with penetration testing methodologies
  
• Excellent written and verbal communication (research, reports, presentations)
  

• 
  
• Experience attacking or defending LLMs (prompt injection, jailbreaks, model extraction)
  
• Background in financial services security or fraud
  
• Published security research or CVEs discovered
  
• Speaking experience at security conferences
  
• Certifications: OSCP, GPEN, CEH, or similar
  
• CTF competition experience or bug bounty hunting
  

• 
  
• PhD or MS in Computer Science, Security, or ML
  
• Experience with federated learning or privacy‑preserving ML
  
• Knowledge xcfaprz of cryptography and secure computation
  
• Familiarity with payment systems and PCI‑DSS
  
• Open source contributions to security tools
  

Full‑time

€45,000.00‑€75,000.00 per year

• 
  
• Company pension
  
• Private medical insurance
  
• Work from home
  

Dublin, County Dublin: reliably commute or plan to relocate before starting work (required)

Do you currently have the legal right to work in Ireland for this role without requiring employer sponsorship now or in the future?

• 
  
• Security analysis: 3 years (required)
  
• Python: 3 years (required)
  
• Machine learning: 3 years (required)
  

Ireland (required)

In person

MOOFWD LIMITED

Senior (5+ years of experience)