Backend Engineer

About the role

Arena Intelligence is a platform for evaluating AI models in real-world scenarios. Founded by researchers from UC Berkeley's SkyLab, we aim to measure and advance AI technology, making it accessible and understandable for everyone. Our platform, Arena, allows tens of millions of users to evaluate AI systems and share their preferences, which helps us understand how these systems perform in actual work environments. We collaborate with leading AI labs, enterprises, and researchers to develop and refine AI models.

What You'll Do

• Build API-based products from the ground up.
• Design and ship the low-latency, high-reliability APIs and services that power Leaderboards, Evals, and Arena data products.
• Turn evaluations into product.
• Partner with the research team to take novel eval methods and make them durable, full-featured products.
• Ship enterprise-grade backends.
• Usage metering, cost attribution, billing integration, authentication, RBAC, multi-tenancy, and audit logging.
• Own the data architecture.
• Unify our public and private evaluation data, design schemas that hold up as the product grows, and make Arena’s data queryable, consistent, and fast.
• Flex across the stack.
• Contribute to the backend of our Leaderboards and Evals platforms when needed, helping unify our public and private data architectures.

What We're Looking For

• 5+ years of backend engineering experience, with meaningful time spent on building product facing APIs, services and data systems at scale.
• Strong proficiency in a modern backend language — Go preferred — and the judgment to design APIs other engineers and customers will live with for years.
• Solid data fundamentals. You’re comfortable modeling, querying, and scaling Postgres, and you know when to reach for Redis, a queue, or a warehouse.
• Experience composing services into products — integrating payments, auth, analytics, or data pipelines into something coherent and reliable.
• A product-oriented mindset. You think about the developer experience of your APIs, not just the implementation. You ask “why” before “how.”
• Comfort with ambiguity. We’re a startup. Scope is fluid, context shifts, and you’ll wear many hats. That should sound exciting, not stressful.

Nice to Have

• Experience with LLM provider APIs (OpenAI, Anthropic, Google, etc.) and the realities of building on them: streaming, token accounting, rate limits, model-specific quirks.
• Background in ML infrastructure, model serving, or evaluation frameworks.
• Experience building enterprise-ready features: SSO, RBAC, audit logs, multi-tenancy.
• Experience building billing and usage infrastructure around systems like Stripe, Metronome, and Orb.
• Familiarity with the modern AI stack (vLLM, LiteLLM, LangChain, etc.).