Software Engineer, Safeguards Labs at Anthropic — task breakdown

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 Safeguards Labs is a new team operating at the intersection of research and engineering, chartered to investigate novel safety methods that protect Claude and the people who use it. We prototype new approaches to safe models, usage safeguards, and production safety, pressure-testing ideas before they graduate into production systems run by our partner Safeguards teams. We're hiring software engineers to partner with our research engineers and turn promising prototypes into reliable, production-grade safeguards. The team is small, so each engineer has substantial latitude over what they work on and high leverage on the team's direction. Key responsibilities Take research prototypes and harden them into production services that integrate with Anthropic's real-time safeguards path. Build data and evaluation infrastructure that lets the team iterate on prototypes quickly and measure whether safeguards actually work, including in agentic settings. Own deployment, monitoring, and reliability for systems Labs ships. Build internal tooling that helps investigators surface and act on abuse patterns. Collaborate with research engineers on scoping and contribute to decisions about which prototypes are ready to graduate. Minimum qualifications Strong proficiency in Python and comfort working with large datasets. A track record of designing, building, and operating production backend systems or data pipelines. Experience taking software from prototype to production, including testing, monitoring, and reliability work. Working familiarity with how large language models operate, even if LLMs aren't your primary background. Care about the societal impacts of AI and want your work to directly reduce real-world harm. Preferred qualifications At least 5 years of software engineering experience. Experience deploying ML systems or classifiers into production. Background in trust and safety, integrity, fraud detection, threat intelligence, or adversarial ML. Experience building developer-facing tooling or platforms that accelerate research workflows. Familiarity with evaluation methodologies for language models. Experience with agentic environments. A history of partnering with researchers and successfully transferring prototypes into production. 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. Annual Salary: $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 rele

Software Engineer, Safeguards Labs

Classified Tasks (8)

Augment (7)

Human-Only (1)

Job description