Research Scientist, Interpretability
3 weeks ago
Anthropic's mission is to create reliable, interpretable, and steerable AI systems that benefit society as a whole.
We're a team of researchers, engineers, policy experts, and business leaders working together to build beneficial AI systems.
About the RoleWe're seeking researchers and engineers to join our Interpretability team, which aims to reverse engineer how trained models work.
Our team believes that a mechanistic understanding is the most robust way to make advanced systems safe.
We're focused on mechanistic interpretability, which involves discovering how neural network parameters map to meaningful algorithms.
Some useful analogies might be to think of us as trying to do 'biology' or 'neuroscience' of neural networks, or as treating neural networks as binary computer programs we're trying to 'reverse engineer'.
We've recently shown that we can extract millions of meaningful features from Anthropic's production Claude 3.0 Sonnet model, along with an initial demonstration of how we can use these features to change the model's behavior by creating 'Golden Gate Claude'.
Achieving these results required a large engineering effort, including optimizing sparse autoencoders (SAEs) across many GPUs, and building tools to visualize millions of features.
Work like this is central to our roadmap of using mechanistic interpretability to improve the safety of LLMs like Claude.
A few places to learn more about our work and team are this introduction to Interpretability from our research lead, Chris Olah; a discussion of our work on the Hard Fork podcast produced by the New York Times, and this blog post (and accompanying video) sharing more about some of the engineering challenges we'd had to solve to get these results.
We collaborate with teams across Anthropic, such as Alignment Science and Societal Impacts, to use our work to make Anthropic's models safer.
Responsibilities- Implement and analyze research experiments, both quickly in toy scenarios and at scale in large models.
- Set up and optimize research workflows to run efficiently and reliably at large scale.
- Build tools and abstractions to support rapid pace of research experimentation.
- Develop and improve tools and infrastructure to support other teams in using Interpretability's work to improve model safety.
- You have 5-10+ years of experience building software.
- You are highly proficient in at least one programming language (e.g., Python, Rust, Go, Java) and productive with Python.
- You have a strong ability to prioritize and direct effort toward the most impactful work and are comfortable operating with ambiguity and questioning assumptions.
- You want to learn more about machine learning research and its applications and collaborate closely with researchers.
- You care about the societal impacts and ethics of your work.
- Designing a code base so that anyone can quickly code experiments, launch them, and analyze their results without hitting bugs.
- Optimizing the performance of large-scale distributed systems.
- Collaborating closely with researchers, ML engineers, or data scientists.
- Language modeling with transformers.
- GPUs or PyTorch.
- Building Garcon, a tool that allows researchers to easily access LLMs internals from a Jupyter notebook.
- Setting up and optimizing a pipeline to efficiently collect petabytes of transformer activations and shuffle them.
- Profiling and optimizing ML training, including parallelizing to many GPUs.
- Make launching ML experiments and manipulating+analyzing the results fast and easy.
- Creating an interactive visualization of attention between tokens in a language model.
Anthropic's compensation package consists of three elements: salary, equity, and benefits.
We are committed to pay fairness and aim for these three elements collectively to be highly competitive with market rates.
Equity will be a major component of the total compensation for eligible roles.
We aim to offer higher-than-average equity compensation for a company of our size, and communicate equity amounts at the time of offer issuance.
US Benefits
- The following benefits are for our US-based employees:
- Optional equity donation matching.
- Comprehensive health, dental, and vision insurance for you and all your dependents.
- 401(k) plan with 4% matching.
- 22 weeks of paid parental leave.
- Unlimited PTO - most staff take between 4-6 weeks each year, sometimes more.
- Stipends for education, home office improvements, commuting, and wellness.
- Fertility benefits via Carrot.
- Daily lunches and snacks in our office.
- Relocation support for those moving to the Bay Area.
UK Benefits
- The following benefits are for our UK-based employees:
- Optional equity donation matching.
- Private health, dental, and vision insurance for you and your dependents.
- Pension contribution (matching 4% of your salary).
- 21 weeks of paid parental leave.
- Unlimited PTO - most staff take between 4-6 weeks each year, sometimes more.
- Health cash plan.
- Life insurance and income protection.
- Daily lunches and snacks in our office.
This compensation and benefits information is based on Anthropic's good faith estimate for this position as of the date of publication and may be modified in the future.
Employees based outside of the UK or US will receive a different benefits package.
The level of pay within the range will depend on a variety of job-related factors, including where you place on our internal performance ladders, which is based on factors including past work experience, relevant education, and performance on our interviews or in a work trial.
How We're DifferentWe believe that the highest-impact AI research will be big science.
At Anthropic, we work as a single cohesive team on just a few large-scale research efforts.
We value impact - advancing our long-term goals of steerable, trustworthy AI - rather than work on smaller and more specific puzzles.
We view AI research as an empirical science, which has as much in common with physics and biology as with traditional efforts in computer science.
We're an extremely collaborative group, and we host frequent research discussions to ensure that we are pursuing the highest-impact work at any given time.
As such, we greatly value communication skills.
The easiest way to understand our research directions is to read our recent research.
This research continues many of the directions our team worked on prior to Anthropic, including GPT-3, Circuit-Based Interpretability, Multimodal Neurons, Scaling Laws, AI & Compute, Concrete Problems in AI Safety, and Learning from Human Preferences.
Come work with us
Anthropic is a public benefit corporation headquartered in San Francisco.
We offer competitive compensation and benefits, optional equity donation matching, generous vacation and parental leave, flexible working hours, and a lovely office space in which to collaborate with colleagues.
-
Research Scientist, Interpretability
4 weeks ago
San Francisco, California, United States Anthropic Full timeAbout AnthropicAnthropic's mission is to create reliable, interpretable, and steerable AI systems. We aim to develop AI that is safe and beneficial for our users and for society as a whole.Our team is a quickly growing group of committed researchers, engineers, policy experts, and business leaders working together to build beneficial AI systems.About the...
-
Research Scientist
4 days ago
San Francisco, California, United States RI Research Instruments GmbH Full timeAbout AnthropicAnthropic is a pioneering AI safety and research company dedicated to building trustworthy, steerable, and interpretable AI systems. Our mission is to create AI that benefits society as a whole, while ensuring its safety and reliability.Job DescriptionWe are seeking a highly skilled Research Scientist to join our team. As a Research Scientist,...
-
Postdoctoral Research Scientist
3 weeks ago
San Francisco, California, United States Gladstone Institutes Full timeJoin Our Team as a Postdoctoral Research ScientistWe are seeking a highly motivated and talented postdoctoral research scientist to join our team at the Gladstone Institutes. As a postdoctoral research scientist, you will have the opportunity to work on cutting-edge research projects in the field of integrative neuroscience.About the PositionThis is a...
-
Cardiology Research Scientist
3 days ago
San Francisco, California, United States University of California , San Francisco Full timeJob Title: Translational Scientist - Valvular Heart DiseaseThe University of California, San Francisco, Department of Medicine, Division of Cardiology, is seeking a highly qualified translational scientist to join our team. As a key member of our research group, you will be responsible for conducting innovative research in valvular heart disease, with a...
-
Ocular Research Scientist
4 weeks ago
San Diego, California, United States RPM ReSearch Full timeJob Title: Ocular Research ScientistWe are seeking a highly skilled Ocular Research Scientist to join our team at RPM ReSearch. As a key member of our research team, you will be responsible for conducting preclinical ophthalmic studies, developing and executing research studies, and training junior team members.Key Responsibilities:Assume the functional role...
-
Ocular Research Scientist
3 weeks ago
San Diego, California, United States RPM ReSearch Full timeJob Title: Ocular Research ScientistWe are seeking a highly skilled Ocular Research Scientist to join our team at RPM ReSearch. As a key member of our research team, you will be responsible for designing and conducting preclinical ophthalmic studies, developing and executing research studies to expand our research capabilities, and training junior team...
-
Ocular Research Scientist
2 weeks ago
San Diego, California, United States RPM ReSearch Full timeJob Title: Ocular Research ScientistWe are seeking a highly skilled Ocular Research Scientist to join our team at RPM ReSearch. As a key member of our research team, you will be responsible for designing and conducting preclinical studies to develop and support in vivo models for ocular disorders.Key Responsibilities:Assume the functional role of Principal...
-
Veterinary Research Scientist
3 weeks ago
San Diego, California, United States RPM ReSearch Full timeJob Title: Veterinary Research ScientistAt RPM ReSearch, we are seeking a highly skilled Veterinary Research Scientist to join our team. As a key member of our research team, you will be responsible for developing and supporting in vivo models to screen therapeutics and devices being developed for various disorders.Key Responsibilities:Perform surgical...
-
Senior Research Scientist
2 days ago
San Francisco, California, United States Future House USA Full timeAbout FutureHouseFutureHouse is a cutting-edge, non-profit AI-for-science lab that leverages AI to automate research in biology and other complex sciences. Backed by Eric Schmidt, our mission is to develop AI systems that can accelerate scientific research and drive breakthroughs in disease cures, climate change solutions, and other species-accelerating...
-
Research Scientist
3 days ago
South San Francisco, California, United States ICONMA Full timeJob Title: Research AssociateJoin ICONMA as a Research Associate and contribute to the development of innovative therapeutic solutions.Job Summary:We are seeking a highly motivated and detail-oriented Research Associate to join our team. The successful candidate will design and implement invitro and invivo studies to address ADME questions of protein and...
-
Research Scientist
2 weeks ago
San Francisco, California, United States University of California , San Francisco Full timeJob Title: Research ScientistWe are seeking a highly motivated Research Scientist to join our team at the University of California, San Francisco. The successful candidate will have a strong background in computational biology and molecular biology, with expertise in single-cell and spatial genomics, machine learning, statistics, and molecular biology...
-
Research Scientist
3 weeks ago
San Francisco, California, United States NobleAI Full timeAbout NobleAINobleAI is a pioneering company that leverages Science-Based AI technology to transform materials development strategies. Our mission is to unlock the potential of artificial intelligence to build a sustainable world.Job DescriptionWe are seeking a highly skilled Research Scientist to join our team. As a Research Scientist, you will be...
-
Research Scientist
3 weeks ago
San Francisco, California, United States Northern California Institute for Research and Education Full timeJob Title: Research ScholarAre you a scientist looking to make a profound difference in the field of HIV research? We are seeking a highly motivated and experienced Research Scholar to join our team at the Northern California Institute for Research and Education (NCIRE).Job Summary:The Research Scholar will work under the supervision of Dr. Steven Yukl, a...
-
Research Scientist
4 weeks ago
San Francisco, California, United States NobleAI Full timeAbout NobleAINobleAI is a pioneering company that leverages Science-Based AI technology to transform materials development strategies. Our innovative approach delivers actionable insights and reliable predictions to accelerate development and reduce costs of developing new chemicals, materials, and formulations.Job DescriptionWe are seeking a highly skilled...
-
Research Scientist
55 minutes ago
San Francisco, California, United States Swish Analytics Full timeResearch ScientistSwish Analytics is seeking a highly skilled Research Scientist to accelerate progress on our sports betting algorithms and models for increased accuracy and state-of-the-art performance.The ideal candidate will have a strong background in machine learning and data science, with experience in developing and deploying scalable models. They...
-
Research Scientist
3 days ago
San Diego, California, United States California State University Full timeJob Title: Research ScientistCalifornia State University is seeking a highly skilled Research Scientist to join our team in the School of Public Health. As a Research Scientist, you will play a critical role in advancing global health equity through evidence-based approaches.Job SummaryWe are looking for a talented individual with a strong background in...
-
Research Scientist, Music Analytics
1 month ago
San Francisco, California, United States Amazon Full timeResearch Scientist, Music AnalyticsAmazon Music is seeking a highly skilled Research Scientist to join our team. As a key member of our analytics team, you will play a critical role in measuring and optimizing the effectiveness of our marketing activities.Key ResponsibilitiesCausal Modeling: Develop and implement causal models to evaluate the impact of...
-
Research Scientist
4 days ago
San Francisco, California, United States University of California , San Francisco Full timeJob Title: Research ScientistWe are seeking a highly motivated Research Scientist to join our team at the University of California, San Francisco. The successful candidate will have a strong background in computational biology and molecular biology, with expertise in single-cell and spatial genomics, machine learning, statistics, and molecular biology...
-
Research Scientist
4 weeks ago
San Francisco, California, United States University of California , San Francisco Full timeJob SummaryWe are seeking a highly motivated and experienced researcher to join our team at the University of California, San Francisco. The successful candidate will be responsible for conducting research projects in the laboratory of an established Principal Scientist with minimal guidance.Key ResponsibilitiesDevelop and conduct research projects in the...
-
Research Scientist
4 days ago
San Francisco, California, United States Imbue, Inc. Full timeAbout the RoleWe are seeking a highly accomplished machine learning researcher to join our team at Imbue, Inc. as a Research Scientist. As a Research Scientist, you will be responsible for investigating the fundamental questions of intelligence, knowledge, and understanding in order to develop software with human-level intelligence.Key...
