{"version":"0.1","company":{"name":"YubHub","url":"https://yubhub.co","jobsUrl":"https://yubhub.co/jobs/skill/machine-learning-serving-infrastructure"},"x-facet":{"type":"skill","slug":"machine-learning-serving-infrastructure","display":"Machine Learning Serving Infrastructure","count":1},"x-feed-size-limit":100,"x-feed-sort":"enriched_at desc","x-feed-notice":"This feed contains at most 100 jobs (the most recently enriched). For the full corpus, use the paginated /stats/by-facet endpoint or /search.","x-generator":"yubhub-xml-generator","x-rights":"Free to redistribute with attribution: \"Data by YubHub (https://yubhub.co)\"","x-schema":"Each entry in `jobs` follows https://schema.org/JobPosting. YubHub-native raw fields carry `x-` prefix.","jobs":[{"@context":"https://schema.org","@type":"JobPosting","identifier":{"@type":"PropertyValue","name":"YubHub","value":"job_f53caced-334"},"title":"Software Engineer, Cloud Inference Safeguards","description":"<p>We are seeking a Software Engineer to build and operate the safety, oversight, and intervention mechanisms that protect Claude on third-party cloud service provider (CSP) platforms.</p>\n<p>As the engineer responsible for Safeguards on those surfaces, you will ensure that every request served through our CSP partners is monitored for misuse, enforced against policy, and compliant with the data residency and privacy commitments that enterprise CSP customers expect.</p>\n<p>You will sit at the seam between the Safeguards organisation and the Cloud Inference team: taking classifiers, detection signals, and enforcement policies developed by Safeguards and making them run reliably inside a CSP partner&#39;s infrastructure at serving-path latency and scale.</p>\n<p>Responsibilities:</p>\n<ul>\n<li>Build, deploy and operate real-time safeguards infrastructure,classifiers, rate limits, enforcement actions, and intervention hooks,embedded directly in the third-party CSP inference serving path</li>\n</ul>\n<ul>\n<li>Design and maintain the data residency and privacy architecture for safeguards signals on CSP platforms, ensuring we can detect abuse and monitor model behaviour while honouring regionalisation boundaries and enterprise contractual commitments</li>\n</ul>\n<ul>\n<li>Develop telemetry, logging, and evaluation pipelines that give Safeguards, Policy, and T&amp;S operational teams situational awareness over CSP traffic and close the visibility gap between third-party and first-party serving</li>\n</ul>\n<ul>\n<li>Dive into the CSP serving stack to identify the lowest-impact points to gather signals or introduce interventions without degrading latency, stability, or overall architecture</li>\n</ul>\n<ul>\n<li>Hold a high operational bar: own on-call, drive root-cause analyses and postmortems for safeguards incidents on CSP platforms, and build systems that reduce the human intervention required to keep Claude safe</li>\n</ul>\n<ul>\n<li>Work closely with Safeguards research, Policy &amp; Enforcement, the Cloud Inference team, and CSP partner contacts to turn detection research and policy decisions into production enforcement that works inside a partner&#39;s cloud.</li>\n</ul>\n<p>You may be a good fit if you:</p>\n<ul>\n<li>Have a Bachelor&#39;s degree in Computer Science, Software Engineering, or comparable experience</li>\n</ul>\n<ul>\n<li>Have 4–10+ years of experience in high-scale, high-reliability software development, ideally with exposure to trust &amp; safety, anti-abuse, fraud, or integrity systems</li>\n</ul>\n<ul>\n<li>Are proficient in Python and comfortable working across the stack,from request-path services to data pipelines to internal tooling</li>\n</ul>\n<ul>\n<li>Think adversarially: you can see a system from a bad actor&#39;s perspective, anticipate how they will respond to countermeasures, and design defences in depth rather than single points of enforcement</li>\n</ul>\n<ul>\n<li>Have experience scaling infrastructure to accommodate rapid traffic growth while keeping latency and reliability within tight budgets</li>\n</ul>\n<ul>\n<li>Are deeply interested in the potential transformative effects of advanced AI systems and are committed to ensuring their safe development</li>\n</ul>\n<ul>\n<li>Have strong communication skills and can explain complex technical and risk tradeoffs to non-technical stakeholders across Policy, Legal, and partner organisations</li>\n</ul>\n<ul>\n<li>Enjoy working in a fast-paced, early environment; comfortable with adapting priorities as driven by the rapidly evolving AI space</li>\n</ul>\n<p>Strong candidates may also have experience with:</p>\n<ul>\n<li>Building trust and safety, anti-spam, fraud, or abuse detection and mitigation mechanisms for AI/ML systems, or the infrastructure to support these systems at scale</li>\n</ul>\n<ul>\n<li>Machine learning serving infrastructure (GPUs/TPUs, inference servers, load balancing) and the operational realities of running models in production</li>\n</ul>\n<ul>\n<li>Major cloud platform internals,IAM, Network/service perimeter controls, regional resource constraints, cloud-native logging/monitoring,or experience shipping software that runs inside a partner&#39;s cloud rather than your own</li>\n</ul>\n<ul>\n<li>Data residency, privacy engineering, or compliance-constrained architectures, particularly where telemetry has to stay within regional or contractual boundaries</li>\n</ul>\n<ul>\n<li>Working closely with operational and human-review teams to build custom internal tooling, admin UX, and alerting</li>\n</ul>\n<ul>\n<li>Adversarial mindset: has shipped defences against motivated attackers before, knows what it feels like when they adapt, and can sprint to close a gap before it becomes an incident</li>\n</ul>\n<ul>\n<li>Comfortable operating at the intersection of platform/infra engineering and trust &amp; safety,neither a pure infra engineer nor a pure T&amp;S engineer, but someone who can credibly do both</li>\n</ul>\n<ul>\n<li>Has shipped software that runs inside someone else&#39;s infrastructure (partner cloud, embedded deployment, or similar) and knows how to get things done when you don&#39;t control the whole stack</li>\n</ul>\n<ul>\n<li>Senior enough to own a cross-team seam independently, drive consensus across orgs, and make latency/safety tradeoff calls without escalation</li>\n</ul>\n<ul>\n<li>TypeScript or Rust, and agentic coding tools such as Claude Code</li>\n</ul>\n<p>The annual compensation range for this role is listed below.</p>\n<p>For sales roles, the range provided is the role&#39;s On Target Earnings (&#39;OTE&#39;) range, meaning that the range includes both the sales commissions/sales bonuses target and annual base salary for the role.</p>\n<p>Annual Salary: $405,000-$485,000 USD</p>\n<p style=\"margin-top:24px;font-size:13px;color:#666;\">XML job scraping automation by <a href=\"https://yubhub.co\">YubHub</a></p>","url":"https://yubhub.co/jobs/job_f53caced-334","directApply":true,"hiringOrganization":{"@type":"Organization","name":"Anthropic","sameAs":"https://www.anthropic.co/","logo":"https://logos.yubhub.co/anthropic.co.png"},"x-apply-url":"https://job-boards.greenhouse.io/anthropic/jobs/5168829008","x-work-arrangement":"hybrid","x-experience-level":"senior","x-job-type":"full-time","x-salary-range":"$405,000-$485,000 USD","x-skills-required":["Python","Cloud service provider (CSP)","Data residency and privacy","Machine learning serving infrastructure","Major cloud platform internals","Data residency, privacy engineering, or compliance-constrained architectures"],"x-skills-preferred":["TypeScript","Rust","Agentic coding tools","Claude Code","Trust and safety","Anti-abuse","Fraud","Integrity systems"],"datePosted":"2026-04-18T15:53:08.973Z","jobLocation":{"@type":"Place","address":{"@type":"PostalAddress","addressLocality":"San Francisco, CA | Seattle, WA"}},"employmentType":"FULL_TIME","occupationalCategory":"Engineering","industry":"Technology","skills":"Python, Cloud service provider (CSP), Data residency and privacy, Machine learning serving infrastructure, Major cloud platform internals, Data residency, privacy engineering, or compliance-constrained architectures, TypeScript, Rust, Agentic coding tools, Claude Code, Trust and safety, Anti-abuse, Fraud, Integrity systems","baseSalary":{"@type":"MonetaryAmount","currency":"USD","value":{"@type":"QuantitativeValue","minValue":405000,"maxValue":485000,"unitText":"YEAR"}}}]}