Staff Software Engineer Platform Connectivity

Humanloop; Greater London; Hybrid; GBP 57,000 - 73,000; Full time

Benefits offered by this job

Competitive compensation

Equity donation matching (optional)

Generous vacation & parental leave

Flexible working hours

Lovely office space

Job summary

Anthropic is building Claude and the connected infrastructure to enable secure external access, with teams spanning San Francisco and London. We are seeking a backend/platform engineer who will design, build, and operate core connectivity infra, own infra reliability, and drive cross-org initiatives.

You will contribute to MCP standards, work with Python/TypeScript SDKs, and help ship scalable, robust solutions in a hybrid London-based role.

Qualifications

• Experience as a backend or platform engineer.
• Familiarity with using AI tools as part of the software development process.
• A product-focused approach to platform work, with emphasis on robust, scalable, and easy-to-use solutions.
• Full ownership of work from design through build, deployment, operations, and iterative improvement.
• Ability to navigate ambiguity and make sound technical decisions independently, ideally in both 0-1 and more mature team or company settings.
• Experience operating production distributed systems, with an understanding of reliability, observability, and incident response at scale.
• Excellent communication skills, with the ability to build consensus across teams and time zones.

Responsibilities

• Design, build, and operate the core connectivity infrastructure behind external tool calls, including the MCP proxy and the OAuth and token management systems.
• Own reliability for infrastructure that other teams and external partners depend on, including SLOs, on-call, incident response, and postmortems.
• Build admin controls and permission models that let enterprise IT govern what agents can do.
• Contribute to the MCP standard and its ecosystem, including the spec and the official Python and TypeScript SDKs.
• Turn ambiguous outcomes into shipped, scoped work and dogfood what we build in the products that consume it.
• Independently scope complex, multi-month projects and drive cross-org alignment through ambiguous problem spaces.
• Make architectural decisions that shape how Anthropic builds and scales its products.
• Partner directly with research to productize cutting-edge capabilities.

Skills

Backend engineering

Platform engineering

AI tools usage

End-to-end ownership

Independent decision making

Reliability & observability

Cross-team communication

Education

Bachelor's degree or equivalent

Tools

MCP

OAuth

Python

TypeScript

Linux

Job description

Salary: £57,000 - 73,000 per year

Requirements

• Experience as a backend or platform engineer
• Familiarity with using AI tools as part of the software development process
• A product-focused approach to platform work, with an emphasis on building solutions that are robust, scalable, and easy to use
• Full ownership of work from design through build, deployment, operations, and iterative improvement
• Ability to navigate ambiguity and make sound technical decisions independently, ideally in both 0-1 and more mature team or company settings
• Experience operating production distributed systems, with an understanding of reliability, observability, and incident response at scale
• Excellent communication skills, with the ability to build consensus across teams and time zones
• Bachelors degree or an equivalent combination of education, training, and/or experience
• A field relevant to the role as demonstrated through coursework, training, or professional experience

Responsibilities

• Design, build, and operate the core connectivity infrastructure behind external tool calls, including the MCP proxy and the OAuth and token management systems
• Own reliability for infrastructure that other teams and external partners depend on, including SLOs, on-call, incident response, and postmortems
• Build admin controls and permission models that let enterprise IT govern what agents can do
• Contribute to the MCP standard and its ecosystem, including the spec and the official Python and TypeScript SDKs
• Turn ambiguous outcomes into shipped, scoped work and dogfood what we build in the products that consume it
• Independently scope complex, multi-month projects and drive cross-org alignment through ambiguous problem spaces
• Make architectural decisions that shape how Anthropic builds and scales its products
• Partner directly with research to productize cutting-edge capabilities

Technologies

• AI
• API
• Backend
• Claude Code
• MCP
• OAuth
• Python
• TypeScript
• Linux

More

We are Anthropic, a public benefit corporation headquartered in San Francisco, and our mission is to create reliable, interpretable, and steerable AI systems that are safe and beneficial for our users and society as a whole. Our Connectivity team is building Claude to be the most connected AI, working across claude.ai, Claude Code, Cowork, and the API, with a focus on secure external access, enterprise trust, OAuth at scale, and reliable proxy infrastructure. The team spans San Francisco and London, and we collaborate closely across Anthropic to deliver impact across our products. We offer

• competitive compensation and benefits
• optional equity donation matching
• generous vacation and parental leave
• flexible working hours
• a lovely office space to collaborate with colleagues

The role includes a location preference for candidates based in NY, SEA, SF, or the Bay Area, with a hybrid policy that currently expects staff in the office at least 25% of the time.

last updated 36 week of 2026