Staff Software Engineer: Compute

We need to output HTML fragment with sections: headings using

for section headings like About the role, Responsibilities, Requirements, Qualifications, Skills, Benefits, Pay, Schedule. Only include sections that have real specific content. We must not repeat job title as heading. Must not include Job ID etc. Remove boilerplate, navigation, legal, EEO, scam warning, duplicated lines, application instructions. Must preserve all substantive info. We need to parse the posting: It includes: - About Anthropic (mission description) - About The Role (description) - Responsibilities (list) - You may be a good fit if you (list of qualifications) - Strong candidates may also have (list) - Candidates need not have 100% of the skills listed above (maybe not needed) - Formal certifications or education credentials (maybe not needed) - Direct machine learning or AI research experience (maybe not needed) - Deadline to apply: None. Applications will be reviewed on a rolling basis. (application instruction -> remove) - The annual compensation range for this role is listed below. For sales roles... (but this is not sales role) but they give Annual Salary $320,000—$485,000 USD. So we have Pay section. - 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. (application encouragement -> maybe remove as boilerplate) - Not all strong candidates will meet every single qualification as listed. (boilerplate) - Research shows that people who identify as being from underrepresented groups are more prone to experiencing imposter syndrome... (EEO boilerplate) remove. - We think AI systems like the ones we're building have enormous social and ethical implications... (maybe keep? It's about mission? Might be considered boilerplate but it's about representation; could be considered EEO. Safer to remove.) - Your safety matters to us... (scam warning) remove. - How We're Different (description about research) maybe keep as part of About Anthropic? Could be separate section but not required headings. Could be part of About Anthropic. - Guidance on Candidates' AI Usage: Learn about our policy for using AI in our application process. (application instruction) remove. - Posted by Anthropic on their own careers page... (metadata) maybe drop. - View original / apply → More at Anthropic (navigation) remove. - Then list of other job postings (more at Anthropic) remove. We need to include sections: About the role (maybe we already have About The Role). Responsibilities. Requirements/Qualifications/Skills. Benefits? The posting mentions benefits: "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." That's benefits. Also Pay: salary range. Schedule: location-based hybrid policy (office at least 25% of time). So we can include Schedule section. We must not create sections with filler like "commensurate with experience". We have actual content. Thus sections: - About the role (maybe combine About Anthropic and About The Role? The instruction: use

for section headings (e.g. About the role, Responsibilities, Requirements, Qualifications, Skills, Benefits, Pay, Schedule). So we should have headings exactly those strings if content exists. We have content for About the role: we can combine About Anthropic and About The Role into a prose under About the role heading. Responsibilities: we have list. Requirements: maybe combine "You may be a good fit if you" and "Strong candidates may also have" and education/field/min years etc. Could be under Requirements. Qualifications: maybe separate? But we can put all under Requirements. However instruction says we can have Requirements, Qualifications, Skills as separate headings if we have content. We have qualifications list; skills list maybe overlapping. Could separate: Requirements (education, experience), Qualifications (the "You may be a good fit if you" list), Skills (maybe the "Strong candidates may also have" list). But we need to avoid thin sections. Might be better to combine into Requirements and Qualifications. But we can follow instruction: include a section only when posting has real specific content. We have content for Requirements (education, field, min years, location policy, visa sponsorship). We have content for Qualifications (the "You may be a good fit if you" list). We have content for Skills (the "Strong candidates may also have" list). Benefits: we have benefits description. Pay: salary range. Schedule: hybrid policy. Thus we will output sections: About the role, Responsibilities, Requirements, Qualifications, Skills, Benefits, Pay, Schedule. We must not include headings with empty content. Now we need to extract precise content, preserving all substantive info, not inventing or summarizing away detail. Let's gather content. About the role: combine About Anthropic paragraph and About The Role paragraph. 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: "At Anthropic, we're building AI systems that are safe, beneficial, and transformative. Our mission is to develop AI that benefits humanity, and we believe the most powerful capabilities emerge when we thoughtfully bridge the gap between research breakthroughs and real-world applications. Frontier AI runs on datacenters, and the world is in the middle of the largest infrastructure buildout in a generation. The binding constraint on progress is increasingly everything around the chips: land, power, permits, equipment, and the design and construction of the buildings themselves. Bringing a single site online involves hundreds of people, thousands of components, and decisions that move enormous amounts of capital. Much of that work still runs on spreadsheets and handoffs. At Anthropic, we're building software and Claude-powered tools to help Anthropic scale out its compute, and we think there's an enormous opportunity to rethink how that work gets done. It's early, it's already having a real impact, and the engineers who join now will shape how one of the most consequential buildouts in the world gets done. We're looking for strong, versatile software engineers who love building for people doing real work in the physical world. You'll embed with the teams that source sites, design buildings, procure equipment, and manage construction, learn their work deeply, and build the tools and systems they rely on every day. Datacenter experience is a big plus, but what matters most is that you can earn the trust of expert operators, model a messy domain cleanly, and move fast." We can combine into a few paragraphs. Responsibilities: list bullet points: - Build the core systems that track a datacenter's lifecycle (sites, designs, bills of materials, equipment, and construction progress) in one trusted, permissioned source of truth - Embed with datacenter, energy, and supply chain teams to understand how the work actually gets done, find the critical path, and build the tools they reach for first - Bring order to messy data by migrating and reconciling spreadsheets and legacy trackers, and integrate with the industry's tools, like construction management, scheduling, and engineering systems - Design for trust: fine-grained permissions, auditability, and data quality for information that steers major investment decisions - Ship early, iterate with users, and cut anything that doesn't help bring compute online sooner - Partner with research to understand new model capabilities and share where they fall short in engineering-heavy, physical-world domains We need to preserve exactly as given. Requirements: includes: - 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 could also include "Deadline to apply: None. Applications will be reviewed on a rolling basis." but that's application instruction, remove. Qualifications (You may be a good fit if you): - Have 8+ years of experience building software, with strong full-stack skills and solid grounding in data modeling, APIs, and databases - Have built software that teams in a physical-world industry depend on, such as datacenters, construction, energy, manufacturing, supply chain, or logistics - Have a track record of zero-to-one work in startup or startup-like environments - Are deeply user-centric: you learn the domain from the people doing the work and validate with them before over-investing - Bring high agency and good judgment about what matters, and hold strong opinions loosely - Communicate clearly across engineering, operations, and research, and care about the societal impacts of your work Skills (Strong candidates may also have): - Experience in datacenters (at a hyperscaler, colocation provider, operator, utility, or engineering firm), or in adjacent fields like construction, logistics, or legal - Experience with the domain's tooling, such as construction management (Procore, Autodesk Construction Cloud), scheduling (Primavera P6), PLM/BOM, ERP and procurement, CAD/BIM, DCIM, or power system studies - A background in electrical, mechanical, or civil engineering, energy systems, or supply chain alongside a software career - Experience building products with large language models Benefits: "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." Pay: "Annual Salary $320,000—$485,000 USD" Schedule: we already have location-based hybrid policy under Requirements but maybe better to put under Schedule. The 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." That's schedule. We should not duplicate. So we can move that to Schedule section and remove from Requirements. Thus Requirements will contain education, field of study, minimum years experience, visa sponsorship. Schedule will contain hybrid policy. Now we need to ensure we don't include boilerplate like "We encourage you to apply even if you do not believe you meet every single qualification." etc. Remove. Now produce HTML fragment. Structure:

About the role

...combined paragraphs...

Responsibilities

• ...
...

Requirements

• 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