Backend Engineer

Arena is the platform for evaluating how AI models perform in the real world. Founded by researchers from UC Berkeley's SkyLab, we're on a mission to measure and advance the frontier of AI for real-world use, and to build the foundation for everyone to understand, shape, and benefit from it.

Tens of millions of people use Arena each month to evaluate how frontier systems handle the work they actually do. The preferences they share power the most transparent, rigorous, and human-centered evaluations in AI. Leading AI labs, enterprises, and independent researchers rely on our work and open datasets to understand how models behave in real workflows: agentic coding, creative generation, professional productivity, and beyond. We go beyond leaderboards and decompose what human experience reveals about AI, so models advance toward the work people actually do.

We're a team of researchers, academics, builders, and creatives from UC Berkeley, Google, Stanford, and DeepMind. We seek truth, move fast, and value craftsmanship, curiosity, and impact over hierarchy. We're building a company where thoughtful, curious people from all backgrounds can do their best work together, in an office culture that radiates excellence, energy, and focus.

Arena Intelligence is looking for a backend engineer to build the products and platforms that sit on top of our evaluation systems - the APIs, services, and data systems that turn Arena’s evals into products that enterprises depend on.

This is the application layer of the Arena Service. Where our infrastructure teams builds the gateways and runtimes beneath - you will work closely with them to build the backends that customers will touch directly. This will include the APIs that expose Arena and enterprise data and the systems that manage usage, billing and multi tenant access. This work spans product surfaces of varying maturity and the data pipelines behind them - zero to one in places and scale-it up in others.

You'll be an early member of our enterprise team, working closely with infrastructure engineers, researchers, and product leadership. We move fast and stay rigorous.

• →

  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 — clean, versioned, and built for the developers who consume them.

• →

  Turn evaluations into product. Partner with the research team to take novel eval methods and make them durable, full-featured products: scoring pipelines, data models, and the APIs that expose them.

• →

  Ship enterprise-grade backends. Usage metering, cost attribution, billing integration, authentication, RBAC, multi-tenancy, and audit logging — the systems enterprise customers expect.

• →

  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.

• 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.

• 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.).