Sign up to access all features of our service.
  • Job search
  • Favorites
  • Create a CV
    New
  • Salaries
  • Subscriptions

Researcher, Alignment & Mechanistic Interpretability

Rebash

OpenAI is seeking a Researcher in Alignment Interpretability in San Francisco. You will develop and execute a research plan on mechanistic interpretability of deep networks, collaborating with a motivated team to advance safe AGI. The role emphasizes publishing techniques, engineering scalable infrastructure to study model internals, and guiding research directions toward practical usefulness and long-term safety. #J-18808-Ljbffr Rebash

Vacancy posted 1 day ago
Similar jobs that could be interesting for youBased on the Researcher, Alignment & Mechanistic Interpretability in San Francisco, CA vacancy
  • # Researcher, Alignment InterpretabilityOpenaionsitefull timeSan FranciscoApply## DescriptionAbout the Team The Interpretability team studies internal representations of deep learning models....  ...and carry out a research plan in mechanistic interpretability, in close... 
    Suggested

    Rebash

    San Francisco, CA
    1 day ago
  • $96.7k - $257.1k

    Position description Researcher, Neuroscience Position Overview...  ...strategies, and generating mechanistic insights into neurodegenerative...  ...development through data interpretation and validation....  ...its public mission and in alignment with our PRIDE values and Principles... 
    Suggested
    Local area

    University of California - San Francisco

    San Francisco, CA
    3 days ago
  •  ...monitorability, auditing methods, and improving alignment. [We were the first to show]( that...  ..., monitoring, and frontier-risk research.We care most about monitorability where...  ...interest in model behavior, alignment, or interpretability. Direct chain-of-thought interpretability... 
    Suggested
    Full time
    Work at office
    Relocation package

    OpenAI

    San Francisco, CA
    5 days ago
  • OpenAI, Inc. seeks exceptional researchers to push the frontier of safety mitigations and to derisk frontier models. You...  ...develop novel safety approaches and apply techniques from interpretability, control, and alignment to ensure deployed models remain safe at scale. You... 
    Suggested

    OpenAI, Inc.

    San Francisco, CA
    1 day ago
  • $96.7k - $257.1k

     ..., CA Position description Professional Researcher- Deitchman Lab Department of Clinical Pharmacy...  ...tissue assays, quantiative LC/MS/MS), interpreting data, reporting the results and...  ...in support of its public mission and in alignment with our PRIDE values and Principles of... 
    Suggested
    Local area

    University of California - San Francisco

    San Francisco, CA
    13 hours ago
  • $141.2k - $257.1k

    Full Professional Researcher - Krummel lab The Krummel lab in the Department of Pathology...  ...patients and experimental conditions. Interpret results in biologically and clinically...  ...in support of its public mission and in alignment with our PRIDE values and Principles of... 
    Local area

    University of California - San Francisco

    San Francisco, CA
    2 days ago
  •  ...Keeping misuse and misalignment safeguards, alignment tools, and security measures on track...  ...the Role We are seeking exceptional researchers who can push the frontier of safety...  ...applying new techniques from domains like interpretability, control, and alignment to ensure the... 

    OpenAI, Inc.

    San Francisco, CA
    1 day ago
  •  ...About the Team The Alignment team at OpenAI is dedicated to ensuring that our AI systems are safe, trustworthy, and consistently aligned...  ...and capability. Our work is at the cutting edge of AI research, focusing on developing methodologies that enable AI to robustly... 
    Full time

    OpenAI

    San Francisco, CA
    5 days ago
  • $350k

     ...Research Engineer / Scientist, AlignmentSan Francisco, CAAbout AnthropicAnthropic's mission is to create reliable, interpretable, and steerable AI systems. We want AI to be safe and beneficial...  ...engineer. As a Research Engineer on Alignment Science, you'll contribute to... 
    Work at office
    Visa sponsorship
    Flexible hours

    anthropic

    San Francisco, CA
    3 days ago
  •  ...About the Team OpenAI's Safety Research organization works to ensure that our most capable...  ...in model evaluations, AI safety, alignment, robustness, or related areas. Have...  ...AI control, model behavior analysis, or interpretability. Experience developing monitoring or... 
    Full time

    openai

    San Francisco, CA
    5 days ago
  • $150k

     ...rigorously, proactively, and continuously fuzz-testing them. We are looking for Research Engineers to help develop our reliability platform, with a focus on: # Data-efficient alignment of evaluation models # Dynamic testing of AI applications # Observability and... 
    Visa sponsorship

    Enboarder

    San Francisco, CA
    2 days ago
  • $184.7k - $324.8k

     ...organization sits at the nexus of these systems—where deep applied research, advanced machine learning, and large language models converge...  ...compression).Understanding of reinforcement learning, policy alignment, or RLHF for improving interactive AI systems.Experience... 
    Relocation

    Apple

    San Francisco, CA
    4 days ago
  •  ...About the role Conduit is a frontier AI research company, training on a new modality of data: brain signals. Our first goal is to decode...  ...is not. We have about 30,000 hours (and counting) of time-aligned brain signals and typing data, from about 1% of San Franciscans... 
    Full time
    Work at office

    Conduit Intelligence

    San Francisco, CA
    4 days ago
  • $116.2k - $146.7k

    Associate Professional Researcher - Andino LabThe Andino Laboratory at UCSF is seeking an Associate Professional Researcher to join the...  ...models, high-throughput and systems-level analyses, and data interpretation relevant to viral pathogenesis and antiviral immunity.The... 

    University of California, San Francisco

    San Francisco, CA
    1 day ago
  •  ...communicate updates, troubleshooting, and results to the team. Interpret results and draw conclusions from multistage experiments with...  ...aberrant data and lab issues to management to gain input and alignment on solution. Write technical reports and communicate technical... 
    Full time
    Temporary work
    Local area

    AbbVie

    San Francisco, CA
    1 day ago
  •  ...company from the ground up.About the RoleWe're hiring an ML researcher/engineer to build the models at the core of our underwriting...  ...detection and statistical significance.Feature engineering and interpretability on large, noisy, high-dimensional data (SQL, Pandas/Polars,... 

    HSF

    San Francisco, CA
    4 days ago
  • $235.5k - $329.5k

     ...experienced Senior Director, Clinical Research Oncology Program Executive (PE) to serve...  ...overall development strategy, ensuring alignment across functions, and leading cross-functional...  ..., clinical trial planning, data interpretation, and key program decisionsRepresent programs... 
    Full time
    Work at office
    Work visa
    3 days per week

    Vir Biotechnology

    San Francisco, CA
    1 day ago
  • $148.5k - $223.9k

     ....The ExperienceWe are looking for a Senior Offensive Security Researcher with an attacker mindset to discover, analyze, and remediate security...  ...remediations. Ensure fixes are scalable, maintainable, and aligned with engineering realities.Lead Secure by Default initiatives... 
    Full time

    Salesforce

    San Francisco, CA
    3 days ago
  • $380k

    About the TeamSafety Research at OpenAI is responsible for ensuring our most capable models can be safely deployed in the real world. The...  ....Our work focuses on making models helpful, reliable, and aligned with safety policies across model types, modalities, and product... 
    Work at office
    Local area
    Flexible hours

    OpenAI

    San Francisco, CA
    1 day ago
  • $150k - $250k

     ...manufacturing, consumer goods, and global social organizations.We research and deploy technologies that power AI-native operations —...  ...evolution. This work bridges reinforcement learning, interpretability, and meta-optimization to pioneer continuously learning enterprise... 
    Work at office
    3 days per week

    Distyl AI

    San Francisco, CA
    1 day ago
  • $132.5k - $179k

     ...million people.The Virtual Expert Platform team uses design and research methods to understand the attitudes, needs, and motivations of...  ...innovation.Synthesize data into clear insights and frameworks that align the team on the most important problems and opportunities. Turn... 
    Self employment
    Remote work
    Worldwide

    Intuit

    San Francisco, CA
    3 days ago
  • $216.3k - $280.8k

    Meet the TeamAt Foundation AI, we are leading frontier AI research across Cisco. Our mission is to advance the state of artificial intelligence...  ...expertise in foundation models, post-training and alignment, LLMs, agentic AI, reinforcement learning, reasoning, efficient... 
    Full time
    Temporary work
    Local area
    Flexible hours

    CISCO Systems

    San Francisco, CA
    4 days ago
  • $131k - $196k

     ...actually happened, and it is ours.We're growing fast and hiring the Research talent to match.We're looking for a Design Researcher to help...  ....Independently scope, prioritize, and manage research projects aligned with team goals.Help shape how research works at MaintainX.... 
    Immediate start

    MaintainX

    San Francisco, CA
    3 days ago
  • Alterra Labs in the United States is seeking an ML Researcher specializing in post-training infrastructure to advance safety and alignment in healthcare and life sciences. You will design and evaluate post-training solutions and contribute to building simulation environments... 

    Alterra Labs

    San Francisco, CA
    2 days ago
  • $96.7k - $257.1k

    Professional Researcher Position Description: The Department of Bioengineering and Therapeutic Sciences (BTS) seeks individuals with strong...  ...or prejudice, in support of its public mission and in alignment with our PRIDE values and Principles of Community. As a condition... 
    Local area
    Worldwide

    University of California, San Francisco

    San Francisco, CA
    13 hours ago
  • $259.2k - $324k

    Scale Labs, Research Scientist — AI Safety and AlignmentAs the leading data and evaluation partner for frontier AI companies, Scale plays...  ...some of the hardest open problems in AI safety: assessing the alignment of frontier models, developing control protocols and... 
    Full time

    Scale AI

    San Francisco, CA
    2 days ago
  • Kelly® Science & Clinical is seeking an AI Research Scientist for a direct hire opportunity with one of our clients, a technology start...  ..., Fc‑fusions, and bispecifics. In this setting, agents must interpret analytical and preclinical data, distinguish genuine quality‑attribute... 

    Kelly

    San Francisco, CA
    1 day ago
  • $96.7k - $257.1k

    Position Description Professional Researcher in Molecular Imaging and Neurobiology of Neurodegenerative Proteinopathies The Institute for...  ...or prejudice, in support of its public mission and in alignment with our PRIDE values and Principles of Community. As a condition... 
    Traineeship
    Local area

    University of California, San Francisco

    San Francisco, CA
    4 days ago
  •  ...California, San Francisco in San Francisco, CA seeks a Professional Researcher in the Deitchman Lab to conduct pharmacology studies for HIV...  ...designing experiments (ex vivo tissue assays, LC/MS/MS), interpreting results, and communicating findings to internal and #J-18808... 

    University of California - San Francisco

    San Francisco, CA
    4 days ago
  •  ...frontier AI systems. 2. Mitigation. Keeping misalignment safeguards, alignment tools, and on track to adequately address extreme threats that...  ...team alternates between performing rigorous hypothesis-driven research and turning our insights into interventions or control systems... 

    OpenAI, Inc.

    San Francisco, CA
    1 day ago

Do you want to receive more vacancies?

Subscribe and receive similar vacancies to Researcher, Alignment & Mechanistic Interpretability. Be the first to apply!