{"html":"<p>AfterQuery builds the expert evaluation data that frontier AI labs use to measure and improve their models. We&#39;re hiring machine learning researchers as contractors to author and solve the analysis problems those evaluations run on, drawn from your own research: experiment design, ablations, evaluation and model behavior. This role is for researchers with hands-on ML research experience. We&#39;re not looking for ML engineers focused on deployment, data engineers or data annotators. Fully remote and async, with no fixed hours.</p>\n<h3>Responsibilities</h3><ul><li>Author realistic ML research problems drawn from your own work: experiment design, ablations, evaluation and failure analysis</li><li>Work each problem through to a reference answer, with the reasoning behind every step</li><li>Catch the research mistakes that look reasonable but only a practitioner would spot</li></ul><h3>Requirements</h3><ul><li>Master&#39;s or PhD in computer science, statistics, mathematics or a related field</li><li>3+ years of full-time ML research after your degree (a postdoc counts, PhD years don&#39;t)</li><li>Hands-on experience designing experiments, running ablations or evaluating models</li><li>Strong Python and a deep learning framework such as PyTorch or JAX</li><li>Able to commit at least 10 hours per week</li></ul><h3>Preferred qualifications</h3><ul><li>Publications at venues such as NeurIPS, ICML, ICLR, ACL or CVPR</li><li>Experience at an industry research lab or university research group</li><li>Clear written English and comfort explaining a result step by step</li></ul>"}