Join Anthropic as a Staff+ Software Engineer to build reliable connectivity infrastructure for AI systems.
Posted by employer 1 month ago
First seen on Joblaze 1 month ago
Last verified on the company career page 17 hours ago
Skills & Technologies
AI in the day-to-day
Familiarity with using AI tools as part of the software development process.
Requirements
Not disclosed in this posting: years of experience.
Benefits
Joblaze summary
In this role, the Staff+ Software Engineer on the Platform Connectivity team at Anthropic will focus on designing and maintaining the infrastructure that enables secure external tool interactions for AI systems. Key skills include backend engineering, experience with OAuth and distributed systems, and a strong emphasis on reliability and scalability. This position is ideal for seasoned engineers who thrive in ambiguous environments and have a track record of driving complex projects from inception to deployment. Anthropic's collaborative culture and commitment to impactful AI research further enhance the appeal of this opportunity.
Joblaze insights
Quick facts
From the original posting
Our mission on the Connectivity team is to make Claude the most connected AI. As agents take on more real-world work, we're taking a leading role in defining how they get access to external systems — safely, with the right permissions, and in ways enterprises can trust. We ship standards and services used by claude.ai, Claude Code, Cowork, and the API. We own the MCP proxy that routes every tool call and the OAuth and token management that keeps connections authenticated. We're also core contributors to the MCP spec — now an open standard under the Linux Foundation — and maintain the official Python and TypeScript SDKs.
We're looking for experienced software engineers to join Connectivity. The team spans San Francisco and London, and you'll work closely with partner teams across Anthropic to deliver impact across all of our products. You'll work on problems where reliability and enterprise trust are critical. This means OAuth at scale, admin controls that let IT govern what agents can do, and proxy infrastructure that is reliable by default.
You'll design, build, and operate the core connectivity infrastructure behind external tool calls — the MCP proxy and the OAuth and token management systems that keep connections authenticated. You'll own reliability for infrastructure that other teams and external partners depend on, including SLOs, on-call, incident response, and postmortems. You'll build the admin controls and permission models that let enterprise IT govern what agents can do, and contribute to the MCP standard and its ecosystem, including the spec and the official Python and TypeScript SDKs. You'll turn ambiguous outcomes into shipped, scoped work, dogfooding what you build in the products that consume it.
You'll independently scope complex, multi-month projects, drive cross-org alignment through ambiguous problem spaces, and make architectural decisions that shape how Anthropic builds and scales its products. You'll partner directly with research to productize cutting-edge capabilities, and will have lasting impact on the platform that hundreds of thousands of companies and internal/external engineers depend on every day.
Deadline to apply: None. Applications will be reviewed on a rolling basis.
Location Preference: Preference will be given to candidates based in NY, SEA, SF or the Bay Area given the current location of team.
The annual compensation range for this role is listed below.
Standard company text repeated across Anthropic's postings is omitted here.