2 months ago

Responsibilities

  • Build clean, versioned, low-latency, high-reliability APIs and services for Leaderboards, Evals, and Arena data products.
  • Turn novel evaluation methods into durable products through scoring pipelines, data models, and APIs.
  • Develop enterprise backend capabilities including usage metering, cost attribution, billing integration, authentication, RBAC, multi-tenancy, and audit logging.
  • Own schemas and data architecture that unify public and private evaluation data and keep it queryable, consistent, and fast.
  • Contribute to backend systems across the Leaderboards and Evals platforms and collaborate with infrastructure engineers, researchers, and product leadership.

Requirements

  • 5+ years of backend engineering experience building product-facing APIs, services, and data systems at scale.
  • Strong proficiency in a modern backend language, with Go preferred, and sound API design judgment.
  • Experience modeling, querying, and scaling Postgres, with familiarity knowing when to use Redis, queues, or a warehouse.
  • Experience composing services into reliable products involving payments, authentication, analytics, or data pipelines.
  • Product-oriented approach focused on API developer experience and understanding customer needs.
  • Comfort working in an ambiguous, fast-moving startup environment.
  • Preferred: experience with LLM provider APIs such as OpenAI, Anthropic, and Google.
  • Preferred: background in ML infrastructure, model serving, or evaluation frameworks.
  • Preferred: experience with SSO, RBAC, audit logs, multi-tenancy, billing, and usage infrastructure.
  • Preferred: experience with Stripe, Metronome, Orb, vLLM, LiteLLM, or LangChain.

Benefits

  • Competitive compensation and equity aligned to the team member’s permanent work location, with base salary range dependent on location.
  • Comprehensive medical, dental, vision, and wellness benefits.
  • Opportunity to work on cutting-edge AI with a small, mission-driven team.
  • Culture emphasizing transparency, trust, and community impact.

Tech Stack

Categories

Arena Intelligence, Inc.

About Arena Intelligence, Inc.

51-200 employees

Created by researchers from UC Berkeley, Arena (formerly LMArena) is a community-powered platform to measure and advance the frontier of AI for real-world use. Tens of millions of builders, researchers, and creative professionals come to Arena to use frontier models and give feedback on their responses, shaping a public leaderboard grounded in real-world use.

Contact me