Software Engineer - Platform

The role

You will build core infrastructure including AI gateways, automated arena runtimes, and serving layers. You will design low-latency APIs, solve streaming problems, and build enterprise-grade systems for model evaluation.

What you will do

• Build API-based products from the ground up
• Design and implement low-latency, high-reliability APIs
• Handle SSE/streaming responses across heterogeneous providers
• Build enterprise-grade infrastructure like rate limiting and authentication
• Build deep observability with distributed tracing and real-time dashboards
• Integrate with core evaluation platform and Arena data
• Contribute to the backend of Leaderboards and Evals platforms

Required qualifications

• 5+ years of backend engineering experience
• Experience with distributed systems, infrastructure, or developer-facing platforms
• Strong proficiency in Go
• Experience with LLM provider APIs
• Product-oriented mindset
• Comfort with ambiguity

Nice to have

• Cloud infrastructure experience (AWS, GCP, or Azure)
• Kubernetes
• Terraform
• Database systems like Postgres and Redis
• Experience building API gateways, proxies, or developer tools
• Background in AI/ML infrastructure, model serving, inference, or evaluation frameworks
• Experience building enterprise-ready features: SSO, RBAC, audit logs, multi-tenancy
• Experience building billing infrastructure around systems like Stripe, Metronome, and Orb
• Familiarity with the modern AI infra stack (vLLM, LiteLLM, LangChain, etc.)

Benefits

• Competitive compensation aligned to the markets where team members are based
• Medical benefits
• Dental benefits
• Vision benefits
• Additional support programs

About the company

Arena is the platform for evaluating how AI models perform in the real world. Founded by researchers from UC Berkeley's SkyLab, the team builds foundational infrastructure for model evaluation.