Software Engineer Platform

You will build and operate the core infrastructure behind online AI evaluation systems. You will design reliable, low-latency APIs, solve streaming and provider-failure challenges, add enterprise infrastructure capabilities, and create observability tools. You will also contribute across backend platforms and integrate evaluation data and customer benchmarks into products.

Responsibilities

• Design and implement low-latency, high-reliability APIs for leaderboards, models, and arenas
• Handle SSE and streaming responses across heterogeneous providers, including failure recovery, fallback, and response normalization
• Build rate limiting, authentication, usage metering, cost attribution, audit logging, and SOC 2 compliance capabilities
• Instrument infrastructure with distributed tracing, latency breakdowns, token-level usage tracking, and real-time dashboards
• Integrate with the evaluation platform, Arena data, and customer-specific benchmarks
• Contribute to the backend of Leaderboards and Evals platforms and help unify public and private data architectures

Requirements

• Approximately 5+ years of backend engineering experience with meaningful distributed systems, infrastructure, or developer-facing platform experience
• Strong proficiency in Go
• Experience with LLM provider APIs and streaming, token management, rate limits, and model-specific quirks
• Product-oriented API development mindset
• Comfort working with ambiguity in a startup environment

Benefits

• Equity
• Comprehensive health and wellness benefits, including medical, dental, vision, and additional support programs