{"schemaVersion":"jobsearcher.job.v1","id":"47e734cdc11832715f44a4e7","url":"https://jobsearcher.com/jobs/47e734cdc11832715f44a4e7","canonicalUrl":"https://jobsearcher.com/jobs/47e734cdc11832715f44a4e7","title":"Research Scientist, Philosophy Program","description":"About Resolution\nResolution does research on how to align artificial superintelligence (ASI). ASI may be developed in the next few years, but it is unclear whether alignment is on track to be ready in the same timeframe. We aim at higher a priori confidence in aligned outcomes by pursuing a portfolio of theory and empirics bets, any one of which — if it succeeds — would meaningfully advance the field. We invest heavily in research automation to accelerate progress, and we believe that stronger alignment theory unlocks higher automation: more principled approaches give us better filters for which directions of automated research are promising.\n\nResolution was founded in 2026 by researchers from UK AISI’s Alignment Team, who ran the £30m Alignment Project, and Timaeus, who pioneered applying singular learning theory to alignment.\n\nFor more information, see our announcement.\n\nAbout Philosophy at Resolution\nWork on AI alignment raises philosophical questions, including what concepts like honesty mean, what character is, what moral competence looks like, which moral theories should guide model behavior, and what research can be delegated to models. Resolution’s philosophy team seeks to advance alignment by examining these questions and testing empirical claims where experimentation can help. Some projects will be primarily conceptual; others will involve collaboration with empirical researchers.\n\nOur initial research agenda is under development, and early hires will help refine its priorities and develop new lines of work. The following gives a flavor of the areas of research we are considering:\n\nConceptual engineering. Alignment research depends on concepts such as honesty, harm, autonomy, and deference, each of which carries multiple senses in ordinary language. We want to understand what it means for a model to represent or operationalize one sense rather than another; how that representation can be changed through training data, context, or other interventions; and which version of a concept a model should employ in a given setting. The goal is to characterize alignment-relevant concepts precisely enough to inform training targets, experimental hypotheses, and evaluation criteria.\n\nCharacter, traits, and constitutions. AI developers increasingly attempt to align models by shaping their character rather than specifying comprehensive sets of rules. But the underlying notions, including trait, persona, disposition, and character, remain poorly understood. We want to clarify the relationships among these concepts, determine which, if any, provides the right unit of analysis for alignment targets, investigate which traits advanced systems should possess, and study empirically how those traits persist, generalize, and interact across contexts.\n\nNormative evaluation of models. What would moral competence in a model consist in? Does it require distinctive capacities, or does it emerge from more general forms of conceptual and practical competence? We want to design experiments that clarify how models make normative judgments and develop evidential standards for determining when, and in which contexts, reliance on those judgments may be warranted.\n\nMoral theories and alignment. Alignment methods presuppose some normative commitments and assumptions. These assumptions can enter system design through, for example, objectives, constitutions, training examples, or evaluation criteria. Sometimes, an explicit commitment to some moral theory is made in model development. Systems shaped by different normative frameworks may behave similarly at current capability levels while diverging substantially as their capabilities increase. We want to understand how different normative structures and moral theories are instantiated in AI systems, and what evidence could help us compare their likely alignment properties.\n\nEpistemic and safety risks of automating conceptual reasoning. Conceptual reasoning work is increasingly being delegated to models, including within alignment research itself. There is a prior question of whether this should happen at all — and, if so, where the limits should be. We want to map the risks and help determine which forms of conceptual work can be delegated, under what conditions, and with what forms of oversight. We are also interested in methods for validating model-generated conceptual work, and in the scientific norms and evidential standards that can help govern AI-assisted alignment research.\n\nWe are interested in proposals for new philosophical research that could substantially improve our understanding of alignment or alter how alignment research is conducted.\n\nAbout the Role\nThe team is new, and the people we hire now will play a significant role in shaping what it becomes. We are hiring research scientists across multiple levels. The scope of the role will depend on the candidate’s experience, research interests, and level of seniority.\n\nAll research scientists may:\n\nLead or contribute to original research projects in philosophy and AI alignment.\n\nIdentify important but underspecified problems and turn them into projects.\n\nConnect philosophical analysis to empirical hypotheses, experimental designs, training approaches, or evaluation methods.\n\nCollaborate closely with researchers from machine learning and other relevant disciplines.\n\nCommunicate research clearly through papers, internal reports, presentations, and external engagement.\n\nContribute to the intellectual culture and development of the philosophy team and Resolution.\n\nDepending on seniority, research scientists may also:\n\nDefine and lead broad or ambiguous areas of research.\n\nHelp set the team’s research agenda and strategic priorities.\n\nInitiate and lead collaborations across Resolution and with external researchers.\n\nSupervise, mentor, or manage more junior researchers.\n\nRepresent the philosophy team in organization-wide research planning.\n\nYou May Be a Good Fit If You\n\nHold a PhD in a relevant field, such as philosophy, cognitive science, psychology, mathematics, or machine learning, or have a record of rigorous research experience.\n\nCan demonstrate your motivations to work on AI alignment, including through previous publications in the field, relevant experiences, or a clear explanation of why you are pivoting your research focus to alignment.\n\nCan identify important questions in areas where the problems, concepts, or success criteria remain unclear.\n\nAre interested in connecting philosophical analysis with empirical and technical research.\n\nCan communicate clearly and collaborate productively with researchers from different disciplinary backgrounds.\n\nStrong Candidates May Also Have\n\nResearch experience in AI safety, AI alignment, or other domains relevant to making ASI futures go well.\n\nThe ability to design, run, or help develop experiments.\n\nPrevious experience working in interdisciplinary research teams.\n\nThe interest and capacity to translate conceptual questions into hypotheses, interventions, or evaluation criteria.\n\nRelevant expertise in areas such as epistemology, philosophy of science, philosophy of language, philosophy of mind, action theory, moral psychology, or ethics.\n\nYou do not need to meet all of these criteria. If you are uncertain whether your background fits, we encourage you to apply.\n\nApplication Process\n\nInitial screener. CV and cover letter review.\n\nInterview. Short interview with the research area lead.\n\nWork test. This will be a timed work test. We’ll share the expected time commitment and other details in advance. You will be compensated for your time, subject to right-to-work constraints.\n\nFinal conversation(s). You may be invited to a follow-up conversation with the philosophy research lead or another member of Resolution’s senior research leadership.\n\nReference checks. With your permission, we’ll contact your references.\n\nApplication deadline. We will begin reviewing applications as soon as they are submitted. There is no hard deadline, but preference will be given to applications received by 28 September 2026 .\n\nLogistics\nSalary: Your salary depends on the scope of work, experience levels, and impact we expect you to have while working at Resolution. The expected range of salaries for this in-person role is:\n\nL3: $236,000\n\nL4: $346,000\n\nL5: $451,000\n\nL6: $670,000\n\nL7: $930,000\n\nStrong research scientists who can reliably own well-scoped projects from conception to completion will typically join at level 3 or 4. Someone capable of leading a larger and more ambiguous area of responsibility would likely join at level 5. We are open to hiring at higher levels for exceptional candidates.\n\nLocation: This role is based in our Berkeley office.\n\nBenefits:\n\n5 weeks of paid vacation per year, in addition to public holidays.\n\nComprehensive healthcare insurance (medical, dental, vision).\n\nUnlimited sick leave to prioritize your well-being.\n\nAn unconditional 401(k) contribution equal to 4% of your salary.\n\nVisa sponsorship: We can sponsor visas for relocation to Berkeley.\n\nStart date: The start date is flexible, although we are prioritizing candidates who can begin as soon as possible.\n\nAI usage: We may use automated systems and AI tools to support recruiting and hiring activities. Final hiring decisions are made by human decision-makers.\n\n#J-18808-Ljbffr","company":"Resolution","rawCompany":"resolution","city":"Berkeley","state":"CA","isRemote":false,"isActive":true,"createdAt":"2026-09-23T04:29:45.044Z","occupations":[{"code":"15-1221.00","title":"Computer and Information Research Scientists","slug":"computer-and-information-research-scientists"},{"code":"25-1126.00","title":"Philosophy and Religion Teachers, Postsecondary","slug":"philosophy-and-religion-teachers-postsecondary"},{"code":"17-2199.08","title":"Robotics Engineers","slug":"robotics-engineers"}],"industries":[{"code":"541715","title":"Research and Development in the Physical, Engineering, and Life Sciences (except Nanotechnology and Biotechnology)","slug":"research-and-development-in-the-physical-engineering-and-life-sciences-except-nanotechnology-and-biotechnology"},{"code":"541720","title":"Research and Development in the Social Sciences and Humanities","slug":"research-and-development-in-the-social-sciences-and-humanities"},{"code":"541690","title":"Other Scientific and Technical Consulting Services","slug":"other-scientific-and-technical-consulting-services"}],"jobPosting":{"@context":"https://schema.org","@type":"JobPosting","title":"Research Scientist, Philosophy Program","description":"About Resolution\nResolution does research on how to align artificial superintelligence (ASI). ASI may be developed in the next few years, but it is unclear whether alignment is on track to be ready in the same timeframe. We aim at higher a priori confidence in aligned outcomes by pursuing a portfolio of theory and empirics bets, any one of which — if it succeeds — would meaningfully advance the field. We invest heavily in research automation to accelerate progress, and we believe that stronger alignment theory unlocks higher automation: more principled approaches give us better filters for which directions of automated research are promising.\n\nResolution was founded in 2026 by researchers from UK AISI’s Alignment Team, who ran the £30m Alignment Project, and Timaeus, who pioneered applying singular learning theory to alignment.\n\nFor more information, see our announcement.\n\nAbout Philosophy at Resolution\nWork on AI alignment raises philosophical questions, including what concepts like honesty mean, what character is, what moral competence looks like, which moral theories should guide model behavior, and what research can be delegated to models. Resolution’s philosophy team seeks to advance alignment by examining these questions and testing empirical claims where experimentation can help. Some projects will be primarily conceptual; others will involve collaboration with empirical researchers.\n\nOur initial research agenda is under development, and early hires will help refine its priorities and develop new lines of work. The following gives a flavor of the areas of research we are considering:\n\nConceptual engineering. Alignment research depends on concepts such as honesty, harm, autonomy, and deference, each of which carries multiple senses in ordinary language. We want to understand what it means for a model to represent or operationalize one sense rather than another; how that representation can be changed through training data, context, or other interventions; and which version of a concept a model should employ in a given setting. The goal is to characterize alignment-relevant concepts precisely enough to inform training targets, experimental hypotheses, and evaluation criteria.\n\nCharacter, traits, and constitutions. AI developers increasingly attempt to align models by shaping their character rather than specifying comprehensive sets of rules. But the underlying notions, including trait, persona, disposition, and character, remain poorly understood. We want to clarify the relationships among these concepts, determine which, if any, provides the right unit of analysis for alignment targets, investigate which traits advanced systems should possess, and study empirically how those traits persist, generalize, and interact across contexts.\n\nNormative evaluation of models. What would moral competence in a model consist in? Does it require distinctive capacities, or does it emerge from more general forms of conceptual and practical competence? We want to design experiments that clarify how models make normative judgments and develop evidential standards for determining when, and in which contexts, reliance on those judgments may be warranted.\n\nMoral theories and alignment. Alignment methods presuppose some normative commitments and assumptions. These assumptions can enter system design through, for example, objectives, constitutions, training examples, or evaluation criteria. Sometimes, an explicit commitment to some moral theory is made in model development. Systems shaped by different normative frameworks may behave similarly at current capability levels while diverging substantially as their capabilities increase. We want to understand how different normative structures and moral theories are instantiated in AI systems, and what evidence could help us compare their likely alignment properties.\n\nEpistemic and safety risks of automating conceptual reasoning. Conceptual reasoning work is increasingly being delegated to models, including within alignment research itself. There is a prior question of whether this should happen at all — and, if so, where the limits should be. We want to map the risks and help determine which forms of conceptual work can be delegated, under what conditions, and with what forms of oversight. We are also interested in methods for validating model-generated conceptual work, and in the scientific norms and evidential standards that can help govern AI-assisted alignment research.\n\nWe are interested in proposals for new philosophical research that could substantially improve our understanding of alignment or alter how alignment research is conducted.\n\nAbout the Role\nThe team is new, and the people we hire now will play a significant role in shaping what it becomes. We are hiring research scientists across multiple levels. The scope of the role will depend on the candidate’s experience, research interests, and level of seniority.\n\nAll research scientists may:\n\nLead or contribute to original research projects in philosophy and AI alignment.\n\nIdentify important but underspecified problems and turn them into projects.\n\nConnect philosophical analysis to empirical hypotheses, experimental designs, training approaches, or evaluation methods.\n\nCollaborate closely with researchers from machine learning and other relevant disciplines.\n\nCommunicate research clearly through papers, internal reports, presentations, and external engagement.\n\nContribute to the intellectual culture and development of the philosophy team and Resolution.\n\nDepending on seniority, research scientists may also:\n\nDefine and lead broad or ambiguous areas of research.\n\nHelp set the team’s research agenda and strategic priorities.\n\nInitiate and lead collaborations across Resolution and with external researchers.\n\nSupervise, mentor, or manage more junior researchers.\n\nRepresent the philosophy team in organization-wide research planning.\n\nYou May Be a Good Fit If You\n\nHold a PhD in a relevant field, such as philosophy, cognitive science, psychology, mathematics, or machine learning, or have a record of rigorous research experience.\n\nCan demonstrate your motivations to work on AI alignment, including through previous publications in the field, relevant experiences, or a clear explanation of why you are pivoting your research focus to alignment.\n\nCan identify important questions in areas where the problems, concepts, or success criteria remain unclear.\n\nAre interested in connecting philosophical analysis with empirical and technical research.\n\nCan communicate clearly and collaborate productively with researchers from different disciplinary backgrounds.\n\nStrong Candidates May Also Have\n\nResearch experience in AI safety, AI alignment, or other domains relevant to making ASI futures go well.\n\nThe ability to design, run, or help develop experiments.\n\nPrevious experience working in interdisciplinary research teams.\n\nThe interest and capacity to translate conceptual questions into hypotheses, interventions, or evaluation criteria.\n\nRelevant expertise in areas such as epistemology, philosophy of science, philosophy of language, philosophy of mind, action theory, moral psychology, or ethics.\n\nYou do not need to meet all of these criteria. If you are uncertain whether your background fits, we encourage you to apply.\n\nApplication Process\n\nInitial screener. CV and cover letter review.\n\nInterview. Short interview with the research area lead.\n\nWork test. This will be a timed work test. We’ll share the expected time commitment and other details in advance. You will be compensated for your time, subject to right-to-work constraints.\n\nFinal conversation(s). You may be invited to a follow-up conversation with the philosophy research lead or another member of Resolution’s senior research leadership.\n\nReference checks. With your permission, we’ll contact your references.\n\nApplication deadline. We will begin reviewing applications as soon as they are submitted. There is no hard deadline, but preference will be given to applications received by 28 September 2026 .\n\nLogistics\nSalary: Your salary depends on the scope of work, experience levels, and impact we expect you to have while working at Resolution. The expected range of salaries for this in-person role is:\n\nL3: $236,000\n\nL4: $346,000\n\nL5: $451,000\n\nL6: $670,000\n\nL7: $930,000\n\nStrong research scientists who can reliably own well-scoped projects from conception to completion will typically join at level 3 or 4. Someone capable of leading a larger and more ambiguous area of responsibility would likely join at level 5. We are open to hiring at higher levels for exceptional candidates.\n\nLocation: This role is based in our Berkeley office.\n\nBenefits:\n\n5 weeks of paid vacation per year, in addition to public holidays.\n\nComprehensive healthcare insurance (medical, dental, vision).\n\nUnlimited sick leave to prioritize your well-being.\n\nAn unconditional 401(k) contribution equal to 4% of your salary.\n\nVisa sponsorship: We can sponsor visas for relocation to Berkeley.\n\nStart date: The start date is flexible, although we are prioritizing candidates who can begin as soon as possible.\n\nAI usage: We may use automated systems and AI tools to support recruiting and hiring activities. Final hiring decisions are made by human decision-makers.\n\n#J-18808-Ljbffr","datePosted":"2026-09-23T04:29:45.044Z","dateModified":"2026-09-23T04:29:45.044Z","hiringOrganization":{"@type":"Organization","name":"Resolution","sameAs":"https://jobsearcher.com"},"jobLocation":{"@type":"Place","address":{"@type":"PostalAddress","addressLocality":"Berkeley","addressRegion":"CA","addressCountry":"US"}},"identifier":{"@type":"PropertyValue","name":"JobSearcher","value":"47e734cdc11832715f44a4e7"},"url":"https://jobsearcher.com/jobs/47e734cdc11832715f44a4e7"}}