Member of Engineering (Evaluations)

📋 Description

• • Member of Engineering (Evaluations) at Poolside AI, Inc. – a remote-first role focused on designing and implementing evaluation infrastructure and tooling for researchers and engineers working toward Artificial General Intelligence.
• • Day-to-day responsibilities include researching and implementing evaluations and benchmarks for base and instruction-following models, collaborating with applied research and product teams to define meaningful metrics that reflect real-world software development progress, and working within a team to plan, discuss, and communicate technical steps clearly.
• • The team is distributed across EMEA and North America, with monthly in-person gatherings and biannual offsites; they combine research and engineering expertise, prioritizing software quality and iterative development to accelerate innovation.
• • In this role, you will deepen your expertise in LLMs, evaluation methodologies, and cross-functional collaboration, contributing directly to measurable progress in AI capabilities while working alongside founding engineers in a high-impact, mission-driven environment.