Security Engineer, Anti-Abuse

About this role

Arena Intelligence is hiring a Security Engineer, Anti-Abuse to build foundational detection and enforcement systems protecting their AI evaluation platform from misuse. You'll own the strategy and implementation for detecting bots, coordinated voting fraud, jailbreaks, and high-severity harms while balancing false-positive costs and user fairness.

What you'll do

• Design and operate detection systems for bots, sybils, coordinated inauthentic voting, and rating manipulation to maintain leaderboard integrity
• Build reversible and auditable enforcement primitives including rate limits, challenges, shadowbans, and account actions
• Detect inference abuse and cost exploitation at the platform layer, plus jailbreak and multi-provider misuse detection
• Develop abuse monitoring and detection for new product launches including web search, web fetch, and live deployment
• Build investigator tooling and production systems for highest-severity harms (CSAM/NCII, violent extremism, self-harm) with legal reporting pipelines
• Partner with Security, Policy, Legal, and model providers on shared attack surfaces and enforcement strategy

What they're looking for

• 6+ years production software engineering under adversarial conditions
• Shipped experience in trust & safety, anti-abuse, anti-fraud, anti-spam, integrity, or risk engineering
• Strong SQL and data analysis for pattern-finding and investigation
• Adversarial mindset with ability to articulate novel attacks before designing defenses
• Backend proficiency in Node.js, TypeScript, Python, or Go
• LLM-specific security including jailbreaks, prompt injection, and tool-use abuse (bonus)
• Experience securing voting, rating, or marketplace platforms against manipulation (bonus)
• Excellent cross-functional communication with engineering, product, policy, and leadership