Description
Mirendil is hiring a research engineer to build evaluation infrastructure for frontier AI models. The role owns frameworks, pipelines, and tooling that measure model behavior across capabilities, including automated evaluation and regression-detection systems, agent-assisted inspection workflows, training-run observability, and collaboration with post-training and reinforcement-learning teams. The position offers a base salary of $300,000–$400,000 USD and a meaningful equity grant, along with competitive benefits.
