{"version":"0.1","company":{"name":"YubHub","url":"https://yubhub.co","jobsUrl":"https://yubhub.co/jobs/skill/factual-grounding"},"x-facet":{"type":"skill","slug":"factual-grounding","display":"Factual Grounding","count":1},"x-feed-size-limit":100,"x-feed-sort":"enriched_at desc","x-feed-notice":"This feed contains at most 100 jobs (the most recently enriched). For the full corpus, use the paginated /stats/by-facet endpoint or /search.","x-generator":"yubhub-xml-generator","x-rights":"Free to redistribute with attribution: \"Data by YubHub (https://yubhub.co)\"","x-schema":"Each entry in `jobs` follows https://schema.org/JobPosting. YubHub-native raw fields carry `x-` prefix.","jobs":[{"@context":"https://schema.org","@type":"JobPosting","identifier":{"@type":"PropertyValue","name":"YubHub","value":"job_3f9344a5-f6e"},"title":"[Expression of Interest] Research Scientist / Engineer, Honesty","description":"<p><strong>About the role</strong></p>\n<p>As a Research Scientist/Engineer focused on honesty within the Finetuning Alignment team, you&#39;ll spearhead the development of techniques to minimize hallucinations and enhance truthfulness in language models.</p>\n<p>Your work will focus on creating robust systems that are accurate and reflect their true levels of confidence across all domains, and that work to avoid being deceptive or misleading.</p>\n<p>Your work will be critical for ensuring our models maintain high standards of accuracy and honesty across diverse domains.</p>\n<p><strong>Responsibilities</strong></p>\n<ul>\n<li>Design and implement novel data curation pipelines to identify, verify, and filter training data for accuracy given the model’s knowledge</li>\n</ul>\n<ul>\n<li>Develop specialized classifiers to detect potential hallucinations or miscalibrated claims made by the model</li>\n</ul>\n<ul>\n<li>Create and maintain comprehensive honesty benchmarks and evaluation frameworks</li>\n</ul>\n<ul>\n<li>Implement techniques to ground model outputs in verified information, such as search and retrieval-augmented generation (RAG) systems</li>\n</ul>\n<ul>\n<li>Design and deploy human feedback collection specifically for identifying and correcting miscalibrated responses</li>\n</ul>\n<ul>\n<li>Design and implement prompting pipelines to generate data that improves model accuracy and honesty</li>\n</ul>\n<ul>\n<li>Develop and test novel RL environments that reward truthful outputs and penalize fabricated claims</li>\n</ul>\n<ul>\n<li>Create tools to help human evaluators efficiently assess model outputs for accuracy</li>\n</ul>\n<p><strong>Requirements</strong></p>\n<ul>\n<li>Have an MS/PhD in Computer Science, ML, or related field</li>\n</ul>\n<ul>\n<li>Possess strong programming skills in Python</li>\n</ul>\n<ul>\n<li>Have industry experience with language model finetuning and classifier training</li>\n</ul>\n<ul>\n<li>Show proficiency in experimental design and statistical analysis for measuring improvements in calibration and accuracy</li>\n</ul>\n<ul>\n<li>Care about AI safety and the accuracy and honesty of both current and future AI systems</li>\n</ul>\n<ul>\n<li>Have experience in data science or the creation and curation of datasets for finetuning LLMs</li>\n</ul>\n<ul>\n<li>An understanding of various metrics of uncertainty, calibration, and truthfulness in model outputs</li>\n</ul>\n<p><strong>Preferred qualifications</strong></p>\n<ul>\n<li>Published work on hallucination prevention, factual grounding, or knowledge integration in language models</li>\n</ul>\n<ul>\n<li>Experience with fact-grounding techniques</li>\n</ul>\n<ul>\n<li>Background in developing confidence estimation or calibration methods for ML models</li>\n</ul>\n<ul>\n<li>A track record of creating and maintaining factual knowledge bases</li>\n</ul>\n<ul>\n<li>Familiarity with RLHF specifically applied to improving model truthfulness</li>\n</ul>\n<ul>\n<li>Worked with crowd-sourcing platforms and human feedback collection systems</li>\n</ul>\n<ul>\n<li>Experience developing evaluations of model accuracy or hallucinations</li>\n</ul>\n<p><strong>Benefits</strong></p>\n<ul>\n<li>Competitive compensation and benefits</li>\n</ul>\n<ul>\n<li>Optional equity donation matching</li>\n</ul>\n<ul>\n<li>Generous vacation and parental leave</li>\n</ul>\n<ul>\n<li>Flexible working hours</li>\n</ul>\n<ul>\n<li>Lovely office space in which to collaborate with colleagues</li>\n</ul>\n<p><strong>Visa sponsorship</strong></p>\n<p>We do sponsor visas! However, we aren&#39;t able to successfully sponsor visas for every role and every candidate. But if we make you an offer, we will make every reasonable effort to get you a visa, and we retain an immigration lawyer to help with this.</p>\n<p style=\"margin-top:24px;font-size:13px;color:#666;\">XML job scraping automation by <a href=\"https://yubhub.co\">YubHub</a></p>","url":"https://yubhub.co/jobs/job_3f9344a5-f6e","directApply":true,"hiringOrganization":{"@type":"Organization","name":"Anthropic","sameAs":"https://www.anthropic.com/","logo":"https://logos.yubhub.co/anthropic.com.png"},"x-apply-url":"https://job-boards.greenhouse.io/anthropic/jobs/4532887008","x-work-arrangement":"hybrid","x-experience-level":"senior","x-job-type":"full-time","x-salary-range":"$350,000-$500,000 USD","x-skills-required":["Python","Language model finetuning","Classifier training","Experimental design","Statistical analysis","Data science","Dataset creation","Uncertainty metrics","Calibration methods"],"x-skills-preferred":["Hallucination prevention","Factual grounding","Confidence estimation","Knowledge integration","RLHF","Crowd-sourcing platforms","Human feedback collection","Evaluations of model accuracy"],"datePosted":"2026-04-18T15:57:52.335Z","jobLocation":{"@type":"Place","address":{"@type":"PostalAddress","addressLocality":"New York City, NY; San Francisco, CA"}},"employmentType":"FULL_TIME","occupationalCategory":"Engineering","industry":"Technology","skills":"Python, Language model finetuning, Classifier training, Experimental design, Statistical analysis, Data science, Dataset creation, Uncertainty metrics, Calibration methods, Hallucination prevention, Factual grounding, Confidence estimation, Knowledge integration, RLHF, Crowd-sourcing platforms, Human feedback collection, Evaluations of model accuracy","baseSalary":{"@type":"MonetaryAmount","currency":"USD","value":{"@type":"QuantitativeValue","minValue":350000,"maxValue":500000,"unitText":"YEAR"}}}]}