Note: The job is a remote job and is open to candidates in USA. The Key Group provides guidance and tools that support school leaders and trusts across the UK. The AI Operations Lead will operate enterprise AI platforms, administer gateways, automate workflows, and manage AI agent and MCP integrations while ensuring governance, security, cost control, and user enablement.
Responsibilities
- AI Gateway & Platform Administration: Oversee the daily operations of our AI gateway (e.g., LiteLLM), managing model routing, rate limits, cataloguing, fallback pathways and access permissions across third-party models like Anthropic and Amazon Bedrock
- Workflow Automation & Optimisation: Build and maintain low-code automations (e.g. n8n) integrating enterprise applications with approved AI services, converting manual processes into secure, auditable, human-in-the-loop workflows
- AI Agent & MCP Integration: Configure, test and deploy AI agents and MCP connections. Enforce least-privilege access across agent knowledge bases while monitoring production behaviour to ensure security and prevent hallucinations
- Governance, Risk & Compliance: Enforce AI governance policies across all models, agents and workflows. Maintain full audit trails and support legal, risk and privacy teams with AI impact assessments and data residency checks
- Monitoring, Reporting & Cost Control: Track token consumption, API spend and usage budgets across external providers. Implement quotas and alert thresholds to ensure usage remains optimized and within budget
- Service Operations & Support: Serve as the primary point of contact for access requests, incidents and operational changes. Maintain runbooks, manage vendor SLAs and resolve platform issues swiftly
- Enablement & Community: Onboard and upskill internal teams on prompt structure and responsible AI tools, fostering a company-wide Community of Practice
Skills
- Proven track record in technology operations, platform administration, application support or service management
- Hands-on experience administering AI platforms/gateways (e.g. LiteLLM) or SaaS automation tools (e.g. n8n, Make, Power Automate)
- Solid understanding of REST APIs, webhooks, JSON structures, RBAC and secret management
- Familiarity with cloud AI providers (Amazon Bedrock, Anthropic) and core GenAI concepts (tokens, context windows, embeddings)
- Strong incident management, system documentation and operational control experience
- Excellent communication skills with the ability to bridge technical concepts and business needs
- Experience in ITIL-aligned or highly regulated, security-sensitive environments
- Exposure to Model Context Protocol (MCP), LLM observability tools (e.g. Langfuse, Datadog) or AWS infrastructure
- Basic Python or JavaScript scripting capabilities for troubleshooting and data mapping
- Awareness of AI governance frameworks (e.g., ISO/IEC 42001, NIST AI RMF) or info-sec standards (ISO 27001, SOC 2)
- Relevant AWS Cloud or AI Governance certifications
Benefits
- Good work-life balance
- The training and support you need to succeed in your role and continue to progress
- A generous holiday allowance
- Flexible hours
- Buying and selling holiday
- Enhanced maternity pay
- Free breakfast, fruit, and drinks
- Regular socials
Company Overview
Company H1B Sponsorship