4 hours ago
Base Salary
$405k - $485k/yr
Responsibilities
- Design, build, and operate the MCP proxy and OAuth and token management infrastructure for external tool calls.
- Own reliability through SLOs, on-call, incident response, and postmortems.
- Build enterprise admin controls and permission models for governing agent actions.
- Contribute to the MCP specification, ecosystem, and official Python and TypeScript SDKs.
- Scope and drive complex multi-month projects, make architectural decisions, and align teams across Anthropic.
- Partner with research teams to productize capabilities and dogfood platform features in consuming products.
Requirements
- Experience as a backend or platform engineer.
- Experience operating production distributed systems and understanding reliability, observability, and incident response at scale.
- Ability to independently make sound technical decisions, navigate ambiguity, and take ownership from design through operations.
- Product-focused approach to building robust, scalable, and usable platform solutions.
- Familiarity with using AI tools in the software development process.
- Strong communication skills and ability to build consensus across teams and time zones.
- Bachelor’s degree or equivalent combination of education, training, and/or experience in a relevant field demonstrated through coursework, training, or professional experience.
Benefits
- Annual compensation range of $405,000—$485,000 USD.
- Hybrid policy requiring staff to work from an Anthropic office at least 25% of the time, with some roles requiring more office time.
- Visa sponsorship with immigration lawyer support where applicable.
- Competitive benefits, optional equity donation matching, generous vacation and parental leave, flexible working hours, and office collaboration space.
Tech Stack
About Anthropic
We're an AI research company that builds reliable, interpretable, and steerable AI systems. Our first product is Claude, an AI assistant for tasks at any scale. Our research interests span multiple areas including natural language, human feedback, scaling laws, reinforcement learning, code generation, and interpretability.