Principal AI Platform Engineer

xdesign; United States; Hybrid; USD 180,000 - 260,000; Full time

Benefits offered by this job

Paid leave and benefits

Private medical insurance

Pension match

Learning and development

Parental/adoption leave

Job summary

xdesign is seeking a principal platform engineer to lead the AI platform connecting engineering teams and client workloads with multiple LLM providers. You will own routing, governance, observability, and scalable operational foundations for reliable AI services.

You will drive API gateway design, lifecycle tooling, access control, and cost/latency optimizations, collaborating across platform, product, and client-facing teams to deliver trusted, scalable AI capabilities.

Qualifications

• Production engineering experience in Python or Go with platform-level impact.
• Experience operating or building API gateways (Kong, Envoy, or Apigee).
• Experience integrating multiple LLM providers with robust routing under pressure.

Responsibilities

• Set technical direction for the AI platform and guide design, delivery, and operation of core components.

Skills

Python or Go

API gateways

LLM integration

RBAC/OIDC

Cross-team communication

Tools

Kong

Envoy

Apigee

Job description

Role overview

Provide principal-level technical leadership for an AI platform that connects engineering teams and client workloads with multiple large-language-model providers. The work spans gateway and routing infrastructure, reusable AI capability orchestration, access control, governance, observability and the operational foundations needed to scale reliable AI services.

Responsibilities

• Set technical direction for the platform and guide the design, delivery and operation of core components.
• Build and evolve an API gateway and routing layer for multiple model providers, including resilient routing and failover strategies suitable for incident conditions.
• Design orchestration and lifecycle tooling that allows AI capabilities and agents to be registered, discovered, promoted and reused.
• Establish and maintain access controls using RBAC and OIDC, alongside disciplined API-key lifecycle management.
• Develop caching, cost and latency optimisation approaches, supported by analytics that measure adoption and reuse.
• Define or contribute to API standards, versioning and promotion workflows while embedding trust, safety, auditability and governance into the platform.

Requirements

• Strong production engineering experience in Python or Go, including the ability to make decisions that influence a platform and its engineering teams.
• Experience operating API gateways such as Kong, Envoy or Apigee, or a demonstrable ability to develop this expertise quickly.
• Experience integrating multiple LLM providers and reasoning about routing, resilience and failover under operational pressure.
• Understanding of RBAC or OIDC and secure management of API credentials.
• Ability to communicate technical direction clearly and work effectively across platform, product and client-facing teams.

Nice to have

• Familiarity with MCP or comparable service-registry and capability-discovery patterns.
• Experience with AI-agent governance, platform observability, adoption measurement or production safety controls.

Benefits and work setup

Flexible hybrid and remote working are available, with hubs in the UK and Bulgaria and occasional travel to client sites or offices.

• 35 days of leave including bank holidays, private medical insurance, enhanced parental and adoption leave, financial coaching, a 5% pension match and 40 hours of paid learning and development.