Arena Intelligence
Software 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
Opens the official application on the employer’s site. No login required.
Arena Intelligence
Arena Intelligence builds a platform for evaluating AI model performance through real-world testing and human preference data, powering insights for AI labs and enterprises. The company is hiring data engineers, security engineers, machine learning scientists, and customer-facing technical roles to scale its evaluation infrastructure, protect against misuse, and deliver custom solutions to customers.
View all jobs at Arena IntelligenceLikely interview questions
- Walk us through a time you detected and stopped a novel abuse pattern. How did you identify it, and what enforcement approach did you take?
- Describe your experience building detection systems for coordinated inauthentic behavior (bots, sybils, voting rings). What signals did you use, and how did you balance detection accuracy against false positives?