Arcada Labs Incorporated

You'll design, build, and own distributed systems and core platform infrastructure end-to-end. You'll **own user-facing product surfaces** and **scale evaluation pipelines** for real-world AI systems. This is a high-impact role at a fast-moving startup backed by top investors.

You'll own **brand systems** and **launch videos** for AI arenas at Arcada, crafting how the world discovers new model capabilities. Working with a small, technical team, you'll shape the visual language of AI and ship creative at the rate models drop.

You'll design and run large-scale evaluations that measure how frontier models perform in real-world workflows, turning millions of human preferences into reliable signals about model capability, taste, and agent behavior. Your work will directly shape public leaderboards and the evaluation tools shared with frontier labs. This role sits at the intersection of **engineering**, **ML**, and **research**, deciding what to evaluate and how to turn results into better rankings and insights.

You'll submit a speculative application to **a leading company** and be considered for **future roles** that match your skills.