Machine Learning Evaluation Specialist - Remote

📋 Description

• • As a Machine Learning Evaluation Specialist, you will design research-grade evaluation tasks that push the boundaries of current AI capabilities by creating problems that state-of-the-art models cannot solve using standard approaches.
• • Your day-to-day work involves proposing original ML problems grounded in your domain expertise, designing evaluation tasks requiring specialized knowledge beyond typical pipelines, assessing AI-generated solutions for correctness and creativity, and documenting where and why models fail.
• • You will join a remote-first team at G2i Inc. focused on advancing AI safety and capability through rigorous, domain-specific benchmarking, collaborating with experts across scientific and technical fields.
• • In this role, you will deepen your impact as a domain expert by shaping how AI is evaluated, publishing implicitly through task design, and contributing to the frontier of ML research without needing to build models or write production code.