{"version":"0.1","company":{"name":"YubHub","url":"https://yubhub.co","jobsUrl":"https://yubhub.co/jobs/skill/experience-with-reinforcement-learning"},"x-facet":{"type":"skill","slug":"experience-with-reinforcement-learning","display":"Experience With Reinforcement Learning","count":2},"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_d35e26ec-593"},"title":"Forward Deployed Engineer, GenAI","description":"<p>About Scale AI</p>\n<p>At Scale AI, our mission is to accelerate the development of AI applications.</p>\n<p>As a Forward Deployed Engineer, you&#39;ll be at the forefront of providing the critical data infrastructure that powers the most advanced AI models, directly influencing how humanity interacts with AI.</p>\n<p>Responsibilities:</p>\n<ul>\n<li>Drive Impact: Directly contribute to the advancement of AI by delivering critical data solutions for leading AI innovators and government agencies.</li>\n</ul>\n<ul>\n<li>Customer Collaboration: Interact daily with our technical customers, understanding their unique challenges and translating them into impactful solutions.</li>\n</ul>\n<ul>\n<li>End-to-End Development: Design, build, and deploy features across the entire stack, from front-end interfaces to back-end systems and infrastructure.</li>\n</ul>\n<ul>\n<li>Rapid Experimentation: Deliver high-quality experiments quickly, iterating quickly to meet customer needs and drive innovation.</li>\n</ul>\n<ul>\n<li>Strategic Influence: Play a key role in shaping our engineering culture, values, and processes, contributing to the growth of our team and the evolution of our product.</li>\n</ul>\n<ul>\n<li>Diverse Projects: Engage in a dynamic mix of designing and deploying cutting-edge data solutions, collaborating with leading AI researchers, and directly influencing the product roadmap.</li>\n</ul>\n<p>Requirements:</p>\n<ul>\n<li>At least 2 years of relevant experience is preferred</li>\n</ul>\n<ul>\n<li>Proven track record of shipping high-quality products and features at scale.</li>\n</ul>\n<ul>\n<li>Strong problem-solving skills and the ability to work independently or as part of a collaborative team.</li>\n</ul>\n<ul>\n<li>Desire to thrive in a fast-paced, dynamic environment.</li>\n</ul>\n<ul>\n<li>Ability to turn business and product ideas into engineering solutions.</li>\n</ul>\n<ul>\n<li>Strong coding abilities and the ability to effectively communicate complex technical concepts to both technical and non-technical audiences.</li>\n</ul>\n<ul>\n<li>Ability to adapt quickly to the ever-changing world of generative AI.</li>\n</ul>\n<ul>\n<li>Excited to join a dynamic, hybrid team in either San Francisco or New York City.</li>\n</ul>\n<p>Benefits:</p>\n<ul>\n<li>Comprehensive health, dental and vision coverage</li>\n</ul>\n<ul>\n<li>Retirement benefits</li>\n</ul>\n<ul>\n<li>A learning and development stipend</li>\n</ul>\n<ul>\n<li>Generous PTO</li>\n</ul>\n<ul>\n<li>Commuter stipend</li>\n</ul>\n<p>Salary Range:</p>\n<p>$179,400-$224,250 USD</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_d35e26ec-593","directApply":true,"hiringOrganization":{"@type":"Organization","name":"Scale AI","sameAs":"https://scale.com/","logo":"https://logos.yubhub.co/scale.com.png"},"x-apply-url":"https://job-boards.greenhouse.io/scaleai/jobs/4593571005","x-work-arrangement":"hybrid","x-experience-level":"mid","x-job-type":"full-time","x-salary-range":"$179,400-$224,250 USD","x-skills-required":["large-scale data processing","distributed systems","machine learning","AI concepts","cloud-based infrastructure"],"x-skills-preferred":["experience working directly with enterprise customers","experience with reinforcement learning with human feedback"],"datePosted":"2026-04-18T16:00:22.735Z","jobLocation":{"@type":"Place","address":{"@type":"PostalAddress","addressLocality":"San Francisco, CA; New York, NY"}},"employmentType":"FULL_TIME","occupationalCategory":"Engineering","industry":"Technology","skills":"large-scale data processing, distributed systems, machine learning, AI concepts, cloud-based infrastructure, experience working directly with enterprise customers, experience with reinforcement learning with human feedback","baseSalary":{"@type":"MonetaryAmount","currency":"USD","value":{"@type":"QuantitativeValue","minValue":179400,"maxValue":224250,"unitText":"YEAR"}}},{"@context":"https://schema.org","@type":"JobPosting","identifier":{"@type":"PropertyValue","name":"YubHub","value":"job_4e0b9271-cdd"},"title":"Research Engineer / Scientist, Alignment Science","description":"<p><strong>About the role:</strong></p>\n<p>You want to build and run elegant and thorough machine learning experiments to help us understand and steer the behavior of powerful AI systems. You care about making AI helpful, honest, and harmless, and are interested in the ways that this could be challenging in the context of human-level capabilities. You could describe yourself as both a scientist and an engineer. As a Research Engineer on Alignment Science, you&#39;ll contribute to exploratory experimental research on AI safety, with a focus on risks from powerful future systems (like those we would designate as ASL-3 or ASL-4 under our Responsible Scaling Policy), often in collaboration with other teams including Interpretability, Fine-Tuning, and the Frontier Red Team.</p>\n<p>Our blog provides an overview of topics that the Alignment Science team is either currently exploring or has previously explored. Our current topics of focus include...</p>\n<ul>\n<li><strong>Scalable Oversight:</strong> Developing techniques to keep highly capable models helpful and honest, even as they surpass human-level intelligence in various domains.</li>\n</ul>\n<ul>\n<li><strong>AI Control:</strong> Creating methods to ensure advanced AI systems remain safe and harmless in unfamiliar or adversarial scenarios.</li>\n</ul>\n<ul>\n<li><strong>Alignment Stress-testing</strong> <strong>:</strong> Creating model organisms of misalignment to improve our empirical understanding of how alignment failures might arise.</li>\n</ul>\n<ul>\n<li><strong>Automated Alignment Research:</strong> Building and aligning a system that can speed up &amp; improve alignment research.</li>\n</ul>\n<ul>\n<li><strong>Alignment Assessments</strong>: Understanding and documenting the highest-stakes and most concerning emerging properties of models through pre-deployment alignment and welfare assessments (see our Claude 4 System Card), misalignment-risk safety cases, and coordination with third-party evaluators.</li>\n</ul>\n<ul>\n<li><strong>Safeguards Research</strong>: Developing robust defenses against adversarial attacks, comprehensive evaluation frameworks for model safety, and automated systems to detect and mitigate potential risks before deployment.</li>\n</ul>\n<ul>\n<li><strong>Model Welfare:</strong> Investigating and addressing potential model welfare, moral status, and related questions. See our program announcement and welfare assessment in the Claude 4 system card for more.</li>\n</ul>\n<p>_Note: For this role, we conduct all interviews in Python and prefer candidates to be based in the Bay Area._</p>\n<p><strong>Representative projects:</strong></p>\n<ul>\n<li>Testing the robustness of our safety techniques by training language models to subvert our safety techniques, and seeing how effective they are at subvertinng our interventions.</li>\n</ul>\n<ul>\n<li>Run multi-agent reinforcement learning experiments to test out techniques like AI Debate.</li>\n</ul>\n<ul>\n<li>Build tooling to efficiently evaluate the effectiveness of novel LLM-generated jailbreaks.</li>\n</ul>\n<ul>\n<li>Write scripts and prompts to efficiently produce evaluation questions to test models’ reasoning abilities in safety-relevant contexts.</li>\n</ul>\n<ul>\n<li>Contribute ideas, figures, and writing to research papers, blog posts, and talks.</li>\n</ul>\n<ul>\n<li>Run experiments that feed into key AI safety efforts at Anthropic, like the design and implementation of our Responsible Scaling Policy.</li>\n</ul>\n<p><strong>You may be a good fit if you:</strong></p>\n<ul>\n<li>Have significant software, ML, or research engineering experience</li>\n</ul>\n<ul>\n<li>Have some experience contributing to empirical AI research projects</li>\n</ul>\n<ul>\n<li>Have some familiarity with technical AI safety research</li>\n</ul>\n<ul>\n<li>Prefer fast-moving collaborative projects to extensive solo efforts</li>\n</ul>\n<ul>\n<li>Pick up slack, even if it goes outside your job description</li>\n</ul>\n<ul>\n<li>Care about the impacts of AI</li>\n</ul>\n<p><strong>Strong candidates may also:</strong></p>\n<ul>\n<li>Have experience authoring research papers in machine learning, NLP, or AI safety</li>\n</ul>\n<ul>\n<li>Have experience with LLMs</li>\n</ul>\n<ul>\n<li>Have experience with reinforcement learning</li>\n</ul>\n<ul>\n<li>Have experience with Kubernetes clusters and complex shared codebases</li>\n</ul>\n<p><strong>Candidates need not have:</strong></p>\n<ul>\n<li>100% of the skills needed to perform the job</li>\n</ul>\n<ul>\n<li>Formal certifications or education credentials</li>\n</ul>\n<p>The annual compensation range for this role is listed below.</p>\n<p>For sales roles, the range provided is the role’s On Target Earnings (&quot;OTE&quot;) range, meaning that the range includes both the sales commissions/sales bonuses target and annual base salary for the role.</p>\n<p>Annual Salary:</p>\n<p>$350,000 \\- $500,000USD</p>\n<p><strong><strong>Logistics</strong></strong></p>\n<p><strong>Education requirements:</strong> We require at least a Bachelor&#39;s degree in a related field or equivalent experience.</p>\n<p><strong>Location-based hybrid policy:</strong> Currently, we expect all staff to be in one of our offices at least 25% of the time. However, some roles may require more time in our offices.</p>\n<p><strong>Visa sponsorship:</strong> 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><strong>We encourage you to apply even if you do not believe you meet every single qualification.</strong> Not all strong candidates will meet every single qualification as listed.  Research shows that people who identify as being from underrepresented groups are more prone to experiencing imposter syndrome and doubting the strength of their candidacy, so we urge you not to exclude yourself prematurely and to submit an application if you&#39;re interested in this work. We think AI systems like the ones we&#39;re building have enormous social and ethical implications. We think this makes representation even more important, and we strive to include a range of diverse perspectives on our team.</p>\n<p><strong>Your safety matters to us.</strong> To protect yourself from potential scams, remember that Anthropic recruits through our website and other job boards, and we will never ask you to pay for any part of the recruitment process.</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_4e0b9271-cdd","directApply":true,"hiringOrganization":{"@type":"Organization","name":"Anthropic","sameAs":"https://job-boards.greenhouse.io","logo":"https://logos.yubhub.co/anthropic.com.png"},"x-apply-url":"https://job-boards.greenhouse.io/anthropic/jobs/4631822008","x-work-arrangement":"hybrid","x-experience-level":"senior","x-job-type":"full-time","x-salary-range":"$350,000 - $500,000USD","x-skills-required":["Python","Machine Learning","Research Engineering","AI Safety","Scalable Oversight","AI Control","Alignment Stress-testing","Automated Alignment Research","Alignment Assessments","Safeguards Research","Model Welfare"],"x-skills-preferred":["Experience authoring research papers in machine learning, NLP, or AI safety","Experience with LLMs","Experience with reinforcement learning","Experience with Kubernetes clusters and complex shared codebases"],"datePosted":"2026-03-08T13:51:34.613Z","jobLocation":{"@type":"Place","address":{"@type":"PostalAddress","addressLocality":"San Francisco, CA"}},"employmentType":"FULL_TIME","occupationalCategory":"Engineering","industry":"Technology","skills":"Python, Machine Learning, Research Engineering, AI Safety, Scalable Oversight, AI Control, Alignment Stress-testing, Automated Alignment Research, Alignment Assessments, Safeguards Research, Model Welfare, Experience authoring research papers in machine learning, NLP, or AI safety, Experience with LLMs, Experience with reinforcement learning, Experience with Kubernetes clusters and complex shared codebases","baseSalary":{"@type":"MonetaryAmount","currency":"USD","value":{"@type":"QuantitativeValue","minValue":350000,"maxValue":500000,"unitText":"YEAR"}}}]}