Adversarial AI Engineer, GoFundMe

• 6–8 years in cybersecurity with a focus on AI/ML security or adversarial ML
• 2+ years specialized LLM security experience (prompt injection, jailbreaking, adversarial prompt crafting)
• Proven red team / penetration testing background on AI systems
• Strong Python programming with ML frameworks (TensorFlow, PyTorch, Hugging Face)
• Deep understanding of ML fundamentals, Neural Networks, transformers (GPT, LLaMA, Claude, BERT) and known vulnerabilities
• Experience testing Agentic AI security testing including agent frameworks (LangGraph, AutoGen, CrewAI, Google ADK, Pydantic AI)
• Skilled in adversarial attack methods: data poisoning, model evasion, membership inference, model extraction
• Knowledge of defense mechanisms: adversarial training, input sanitization, differential privacy, robustness certification
• Hands-on adversarial attack experience: data poisoning, model evasion, membership inference, model extraction
• Familiarity with OWASP Top 10 for LLMs, MITRE ATLAS, NIST AI RMF
• Experience with threat modeling, security architecture, and cloud controls (AWS, GCP, Azure)

Desirable

• Every day, millions turn to us in their most vulnerable moments, and our technology must be safe, resilient, and trustworthy
• We’re looking for an Adversarial AI Engineer who combines offensive security expertise with machine learning depth
• You will execute red team testing against our AI systems, build automated adversarial evaluation pipelines, and deploy defense mechanisms to keep our AI safe
• Beyond technical execution, you’ll influence governance, partner with cross-functional stakeholders, and establish GoFundMe as a thought leader in AI security
• This role is foundational
• You’ll lead red team operations and strengthen our AI/ML systems that power fraud detection, content moderation, and Trust & Safety at scale
• You will also design adversarial testing frameworks, deploy real-time defenses, and set governance for secure AI deployment across GoFundMe’s platform—protecting billions in charitable giving from evolving attack vectors
• Adversarial Testing & Red Teaming
• Execute adversarial testing of LLMs, Agentic AI systems, recommendation models, and fraud detection tools using techniques such as prompt injection, jailbreaking, data poisoning, model inversion, and membership inference attacks
• Develop synthetic attack datasets tailored to fundraising and trust & safety scenarios
• Build Security Frameworks & Defenses
• Develop automated adversarial testing pipelines integrated into CI/CD, create reusable robustness evaluation libraries, and generate synthetic attack datasets for fundraising scenarios
• Build reusable robustness evaluation libraries
• Deploy real-time detection for prompt injection and model evasion, implement input validation, output filtering, adversarial training, and differential privacy mechanisms
• Cross-Functional Security Leadership
• Partner with Trust & Safety on fraud countermeasures
• Collaborate with Product Security on AI threat models and governance
• Work with Data Science to mitigate algorithmic bias and ensure robust defense
• Governance & Policy
• Establish AI security policies, training, and deployment review processes aligned with NIST AI RMF
• Build monitoring and incident response systems for AI security
• Research & Innovation
• Stay current with emerging attack vectors and defense mechanisms
• Contribute to open-source adversarial tools
• Publish and speak externally to advance GoFundMe’s leadership in AI security