Teams at Scale AI

Conduct empirical AI safety research with mentor guidance, owning projects from hypotheses and controlled experiments through analysis and technical writing. Build and debug evaluation harnesses, agent environments, datasets, monitoring methods, and post-training experiments. Investigate model failures, alignment, deception, misuse, multi-agent risks, and evaluation reliability. Produce reproducible code, experiment logs, research analyses, and papers for potential submission to leading machine learning conferences.

Perform part-time quality audits and evaluations of task outputs, define and refine quality benchmarks and scoring rubrics, analyze audit results to produce actionable insights and reports, and recommend process improvements to raise output quality.