Staff AI Platform Engineer

• Own the AI Platform architecture and set its technical vision and standards
• Document the architecture
• Lead the evolution of the AI gateway and model-routing decisions, including provider routing, hybrid and on-prem routing, failover, caching, rate limits and multi-provider compatibility
• Decide the agent orchestration stack
• Design sandboxing and lifecycle management for agents that run code or access internal systems
• Define multi-agent and human-in-the-loop patterns
• Design identity and access control for people and non-human agent identities
• Lead model, tool and MCP allowlists and access tiers
• Work with Legal and Security on EU AI Act and data-classification requirements
• Shape the skills/plugins repository and define the security model for the curated MCP registry
• Standardize tooling for tracing agent decisions, evaluations, drift detection and quality-regression monitoring
• Design cost attribution and allocation for token and compute spend
• Serve as technical escalation point for embedded AI delivery
• Unblock teams, review designs and create golden paths
• Partner with Security teams on threat modelling and controls for prompt injection, data exfiltration and over-privileged tools
• Mentor engineers, run design reviews and RFCs, and represent AI Platform in engineering-wide technical decisions
• Participate in on-call rotation and incident response for production AI services

• 8+ years in software, platform, infrastructure or SRE engineering
• Experience at Staff/Principal level or in a tech-lead role owning architecture across teams
• Strong understanding of LLM and API fundamentals, including context windows, tool use, structured outputs, streaming, prompt caching, and provider API differences
• Hands-on experience designing or running an LLM gateway or similar layer, including build-vs-buy decisions
• Experience with agent orchestration patterns, including multi-agent workflows, delegation, human-in-the-loop approval gates, memory and context management, and token optimization
• Experience working with Security teams on threat modelling, security reviews and risk acceptance for production systems
• Working knowledge of the Model Context Protocol (MCP), including implementing servers, scoping tools, and reviewing third-party servers for security
• Production experience with containers and isolation, including Docker and Kubernetes
• Infrastructure as code experience with Terraform or similar on at least one major cloud; Azure preferred
• Solid grasp of observability, including OpenTelemetry, Prometheus and Grafana, and reliability engineering for non-deterministic AI systems
• Strong coding skills
• Record of influencing without authority, writing RFCs and architecture decision records, gaining team agreement, and explaining technical trade-offs to non-technical stakeholders
• Nice to have: experience with AI evaluation and observability tools
• Nice to have: FinOps experience with usage-based cost models
• Nice to have: familiarity with AI governance frameworks including EU AI Act, NIST AI RMF and ISO/IEC 42001
• Nice to have: experience with AI coding agents and extension models
• Nice to have: hands-on experience designing or evaluating model routing solutions
• Nice to have: experience serving self-hosted or on-prem models
• Nice to have: experience building developer platforms, golden paths or internal developer portals

• Competitive annual salary
• Private health insurance
• Flexible benefits plan allowing employees to tailor part of their compensation package to personal needs
• Annual bonus based on individual performance and company results
• Flexible working hours
• Remote work options