About Anthropic

Anthropic’s mission is to create reliable, interpretable, and steerable AI systems. We want AI to be 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 role:

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'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.

These papers give a simple overview of the topics the Alignment Science team works on: Sleeper Agents: Training Deceptive LLMs that Persist Through Safety Training, Studying Large Language Model Generalization with Influence Functions, Debating with More Persuasive LLMs Leads to More Truthful Answers, Language Models (Mostly) Know What They Know, Measuring Progress on Scalable Oversight for Large Language Models, Measuring Faithfulness in Chain-of-Thought Reasoning, Discovering Language Model Behaviors with Model-Written Evaluations.

Note: Currently, the team has a preference for candidates who are able to be based in the Bay Area. However, we remain open to any candidate who can travel 25% to the Bay Area.

Representative projects:

Testing the robustness of our safety techniques by training language models to subvert our safety techniques, and seeing how effective they are at subverting our interventions.
Run multi-agent reinforcement learning experiments to test out techniques like AI Debate.
Build tooling to efficiently evaluate the effectiveness of novel LLM-generated jailbreaks.
Write scripts and prompts to efficiently produce evaluation questions to test models’ reasoning abilities in safety-relevant contexts.
Contribute ideas, figures, and writing to research papers, blog posts, and talks.
Run experiments that feed into key AI safety efforts at Anthropic, like the design and implementation of our Responsible Scaling Policy.

You may be a good fit if you:

Have significant software, ML, or research engineering experience
Have some experience contributing to empirical AI research projects
Have some familiarity with technical AI safety research
Prefer fast-moving collaborative projects to extensive solo efforts
Pick up slack, even if it goes outside your job description
Care about the impacts of AI

Strong candidates may also:

Have experience authoring research papers in machine learning, NLP, or AI safety
Have experience with LLMs
Have experience with reinforcement learning
Have experience with Kubernetes clusters and complex shared codebases

Candidates need not have:

100% of the skills needed to perform the job
Formal certifications or education credentials

The expected salary range for this position is:

Annual Salary:

$280,000—$690,000 USD

Logistics

Location-based hybrid policy: 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.

Visa sponsorship: We do sponsor visas! However, we aren'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.

We encourage you to apply even if you do not believe you meet every single qualification. 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're interested in this work. We think AI systems like the ones we'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.

How we're different

We 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. And 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.

Apply for this Job

* Required

First Name *

Last Name *

Email *

Phone

Resume/CV

Dropbox Google Drive

(File types: pdf, doc, docx, txt, rtf)

(Optional) Personal Preferences *

How do you pronounce your name?

Website

Publications (e.g. Google Scholar) URL

GitHub URL

When is the earliest you would want to start working with us?

Do you have any deadlines or timeline considerations we should be aware of?

AI Policy for Application *

While we encourage people to use AI systems during their role to help them work faster and more effectively, please do not use AI assistants during the application process. We want to understand your personal interest in Anthropic without mediation through an AI system, and we also want to evaluate your non-AI-assisted communication skills. Please indicate 'Yes' if you have read and agree.

In a paragraph or two, why do you want to work on AI safety at Anthropic? *

In one sentence each, what are three open research questions related to AI safety that you would be interested in contributing to. (We’re especially interested in questions that you think are likely to be neglected by the current AI research ecosystem.) *

Share a link to the piece of work you've done that is most relevant to the Alignment Science team, along with a brief description of the work and its relevance. *

What’s your ideal breakdown of your time in a working week, in terms of hours or % per week spent on meetings, coding, reading papers, etc.? *

In one paragraph, provide an example of something meaningful that you have done in line with your values. Examples could include past work, volunteering, civic engagement, community organizing, donations, family support, etc. *

Will you now or will you in the future require employment visa sponsorship to work in the country in which the job you're applying for is located? *

Additional Information *

Add a cover letter or anything else you want to share.

LinkedIn Profile

Please ensure to provide either your LinkedIn profile or Resume, we require at least one of the two.

Are you open to working in-person in one of our offices 25% of the time? *

Are you open to relocation for this role? *

What is the address from which you plan on working? If you would need to relocate, please type "relocating".

Team Matching *

Which teams or projects are you most interested in? (Note: if none of the teams you select are hiring, we won't proceed with your application at this time, although we may reach out if those teams open roles in the future.)

  Pre-training — The Pre-training team trains large language models that are used by our product, alignment, and interpretability teams. Some projects include figuring out the optimal dataset, architecture, hyper-parameters, and scaling and managing large training runs on our cluster.
  AI Alignment Research — the Alignment team works to train more aligned (helpful, honest, and harmless) models and does “alignment science” to understand how alignment techniques work and try to extrapolate to uncover and address new failure modes.
  Reinforcement Learning – Reinforcement Learning is used by a variety of different teams, both for alignment and to teach models to be more capable at specific tasks.
  Platform – The Platform team builds shared infrastructure used by Anthropic's research and product teams. Areas of ownership include: the inference service that generates predictions from language models; extensive continuous integration and testing infrastructure; several very large supercomputing clusters and the associated tooling.
  Interpretability — The Interpretability team investigates what’s going on inside large language models — in a sense, they are trying to reverse engineer the concepts and mechanics from the inscrutable learned weights of these systems. Their goal is to ensure that AI systems are safe by being able to assess whether they’re doing what we actually want, all the way down to the individual neurons.
  Societal Impacts — Our Societal Impacts team designs and executes experiments that evaluate the capabilities and harms of the technologies we build. They also support the policy team with empirical evidence.
  Product — The Product research team trains, evaluates, and improves upon Claude, integrating all of our research techniques to make our AI systems as safe and helpful as possible.

Voluntary Self-Identification

For government reporting purposes, we ask candidates to respond to the below self-identification survey. Completion of the form is entirely voluntary. Whatever your decision, it will not be considered in the hiring process or thereafter. Any information that you do provide will be recorded and maintained in a confidential file.

As set forth in Anthropic’s Equal Employment Opportunity policy, we do not discriminate on the basis of any protected group status under any applicable law.

Gender

Are you Hispanic/Latino?

Please identify your race

Race & Ethnicity Definitions

If you believe you belong to any of the categories of protected veterans listed below, please indicate by making the appropriate selection. As a government contractor subject to the Vietnam Era Veterans Readjustment Assistance Act (VEVRAA), we request this information in order to measure the effectiveness of the outreach and positive recruitment efforts we undertake pursuant to VEVRAA. Classification of protected categories is as follows:

A "disabled veteran" is one of the following: a veteran of the U.S. military, ground, naval or air service who is entitled to compensation (or who but for the receipt of military retired pay would be entitled to compensation) under laws administered by the Secretary of Veterans Affairs; or a person who was discharged or released from active duty because of a service-connected disability.

A "recently separated veteran" means any veteran during the three-year period beginning on the date of such veteran's discharge or release from active duty in the U.S. military, ground, naval, or air service.

An "active duty wartime or campaign badge veteran" means a veteran who served on active duty in the U.S. military, ground, naval or air service during a war, or in a campaign or expedition for which a campaign badge has been authorized under the laws administered by the Department of Defense.

An "Armed forces service medal veteran" means a veteran who, while serving on active duty in the U.S. military, ground, naval or air service, participated in a United States military operation for which an Armed Forces service medal was awarded pursuant to Executive Order 12985.

Veteran Status

Voluntary Self-Identification of Disability

Form CC-305

Page 1 of 1

OMB Control Number 1250-0005

Expires 04/30/2026

Why are you being asked to complete this form?

We are a federal contractor or subcontractor. The law requires us to provide equal employment opportunity to qualified people with disabilities. We have a goal of having at least 7% of our workers as people with disabilities. The law says we must measure our progress towards this goal. To do this, we must ask applicants and employees if they have a disability or have ever had one. People can become disabled, so we need to ask this question at least every five years.

Completing this form is voluntary, and we hope that you will choose to do so. Your answer is confidential. No one who makes hiring decisions will see it. Your decision to complete the form and your answer will not harm you in any way. If you want to learn more about the law or this form, visit the U.S. Department of Labor’s Office of Federal Contract Compliance Programs (OFCCP) website at www.dol.gov/ofccp.

How do you know if you have a disability?

A disability is a condition that substantially limits one or more of your “major life activities.” If you have or have ever had such a condition, you are a person with a disability. Disabilities include, but are not limited to:

Alcohol or other substance use disorder (not currently using drugs illegally)
Autoimmune disorder, for example, lupus, fibromyalgia, rheumatoid arthritis, HIV/AIDS
Blind or low vision
Cancer (past or present)
Cardiovascular or heart disease
Celiac disease
Cerebral palsy
Deaf or serious difficulty hearing
Diabetes
Disfigurement, for example, disfigurement caused by burns, wounds, accidents, or congenital disorders
Epilepsy or other seizure disorder
Gastrointestinal disorders, for example, Crohn's Disease, irritable bowel syndrome
Intellectual or developmental disability
Mental health conditions, for example, depression, bipolar disorder, anxiety disorder, schizophrenia, PTSD
Missing limbs or partially missing limbs
Mobility impairment, benefiting from the use of a wheelchair, scooter, walker, leg brace(s) and/or other supports
Nervous system condition, for example, migraine headaches, Parkinson’s disease, multiple sclerosis (MS)
Neurodivergence, for example, attention-deficit/hyperactivity disorder (ADHD), autism spectrum disorder, dyslexia, dyspraxia, other learning disabilities
Partial or complete paralysis (any cause)
Pulmonary or respiratory conditions, for example, tuberculosis, asthma, emphysema
Short stature (dwarfism)
Traumatic brain injury

Disability Status

PUBLIC BURDEN STATEMENT: According to the Paperwork Reduction Act of 1995 no persons are required to respond to a collection of information unless such collection displays a valid OMB control number. This survey should take about 5 minutes to complete.

Enter the verification code sent to to confirm you are not a robot, then submit your application.

Security Code *

This application was flagged as potential bot traffic. To resubmit your application, turn off any VPNs, clear the browser's cache and cookies, or try another browser. If you still can't submit it, contact our support team through the help center.

Research Engineer / Scientist, Alignment Science