Software Engineer, Infrastructure, Interpretability

Anthropic Limited; New York (NY); Hybrid; USD 320,000 - 485,000; Full time

Job summary

Anthropic is hiring a Software Engineer, Infrastructure, Interpretability to design, build, and own shared infrastructure for the Interpretability team. You will collaborate with agentic engineering, security, and platform teams to enable researchers to access frontier model weights securely and efficiently.

The role emphasizes security, privacy, data and compute management, and improving developer productivity across the research lifecycle, with a focus on scalable infrastructure in a rapidly

Qualifications

• Proficient in at least one programming language (e.g., Python, Rust, Go, Java).
• Experience building secure and scalable software infrastructure.

Responsibilities

• Design, build, and own shared infrastructure for Interpretability - research environments, data systems, and compute tooling used daily by researchers.
• Lead cross-team efforts across agentic engineering, security, compute, and storage platform teams to serve research needs.
• Identify and resolve developer experience issues across the organization and help move interpretability methods from research to production-grade pipelines.

Skills

Python

Rust

Go

Java

Education

Bachelor's degree

Job description

Software Engineer, Infrastructure, Interpretability

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:

When you see what modern language models are capable of, do you wonder, "How do these things work? How can we trust them?"

The Interpretability team at Anthropic works to understand what's actually happening inside trained models - and applies our best techniques to keep frontier AI safe as it rapidly improves.

Think of us as doing "neuroscience" of neural networks using "microscopes" we build - or reverse-engineering neural networks like binary programs.

60 Minutes segment - see a demo of tooling our team built

New Yorker article - what it's like to work on one of AI's hardest open problems

This role is an early hire on a new infrastructure effort within Interpretability: you'll help define its charter, not just execute it.

Interpretability research requires deep access to frontier models while retaining a high degree of research flexibility. Your job is to build the paved path that makes that access secure by default, private by design, and low-friction for every researcher. The work spans four areas:

Security: design the secure-by-default environments and access patterns that enable deep model access for an organization whose research requires it - done well, the same design improves both our security posture and research productivity.

Privacy: build data-access patterns that ensure policy adherence as our research moves from theory into practical application

Data & Compute Management: manage research data at petabyte scale and make efficient use of large accelerator fleets - storage lifecycle, capacity planning, and scheduling.

Developer experience: agentic engineering, tooling and observability that keep researchers moving fast

In this role, you’ll be deeply embedded alongside Interp Researchers to understand their workflows - building your understanding of the research as you go; at the same time you’ll bridge communication with Anthropic’s wider platform and security teams.. Every hour of researcher friction you remove is multiplied across the whole organization, and the infrastructure you build sets the pace at which interpretability results reach real safety decisions.

Responsibilities:

Design, build, and own shared infrastructure for Interpretability - research environments, data systems, and compute tooling that researchers rely on daily

Lead cross-team efforts with our agentic engineering , security, compute, and storage platform teams, so that company-wide solutions serve research needs

Discover and resolve major organization-wide developer experience issues

Help take interpretability methods from research code to dependable audit pipelines

You may be a good fit if you:

Are highly proficient in at least one programming language (e.g., Python, Rust, Go, Java) and productive with Python

Have significant experience building and operating secure and scalable software infrastructure - cloud systems, distributed systems, or developer tooling

Have strong cross-functional communication skills - equally at home working with researchers and with platform and security teams

Are extremely curious about unfamiliar domains

Have a strong ability to prioritize the most impactful work and are comfortable operating with ambiguity and questioning assumptions

Are curious about interpretability research and its role in AI safety (though no research experience is required!)

Care about the societal impacts and ethics of your work

Strong candidates may also have:

Experience with cloud infrastructure (e.g. GCP or AWS), Kubernetes, networking and infrastructure-as-code

Security engineering experience: identity / auth / access management, sandboxing, red teaming

Experience with data warehousing, large-scale storage systems, and data lifecycle management - especially for research

Experience with compute schedulers and accelerator fleet management

Experience building developer productivity tooling and observability stacks

Experience building tooling to accelerate research teams

Representative Projects:

Design and stand up a hardened research environment where researchers experiment directly on frontier model weights

Build lifecycle management for petabytes of research data - visibility, retention, and cost efficiency

Build self-serve scheduling and capacity tooling

Create the observability that catch infrastructure regressions before they cost researchers valuable time

Role Specific Location Policy:

This role is based in the San Francisco office; however, we are open to considering exceptional candidates for remote work on a case-by-case basis.

The annual compensation range for this role is listed below.

For sales roles, the range provided is the role’s On Target Earnings ("OTE") range, meaning that the range includes both the sales commissions/sales bonuses target and annual base salary for the role.

$320,000 - $485,000 USD

Logistics

Minimum education: Bachelor’s degree or an equivalent combination of education, training, and/or experience

Required field of study:A field relevant to the role as demonstrated through coursework, training, or professional experience

Minimum years of experience: Years of experience required will correlate with the internal job level requirements for the position

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.

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.

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.

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.

Voluntary Self-Identification of Disability

Form CC-305

Page 1 of 1

OMB Control Number 1250-0005

Expires 07/31/2029

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

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.