Staff AI Platform Engineer

This is a fully remote position, open to applicants in Spain.

📋 Description

• Take ownership of the AI Platform architecture and establish its technical vision and standards.

• Create documentation for the architecture.

• Drive the advancement of the AI gateway and model-routing strategies, encompassing provider routing, hybrid and on-premise routing, failover, caching, rate limits, and multi-provider compatibility.

• Determine the agent orchestration stack.

• Design sandboxing and lifecycle management for agents that execute code or access internal systems.

• Define patterns for multi-agent and human-in-the-loop interactions.

• Establish identity and access control mechanisms for both human and non-human agent identities.

• Oversee model, tool, and MCP allowlists along with access tiers.

• Collaborate with Legal and Security teams regarding EU AI Act compliance and data classification requirements.

• Influence the skills/plugins repository and formulate the security model for the curated MCP registry.

• Standardize tools for tracking agent decisions, evaluations, drift detection, and quality regression monitoring.

• Design cost attribution and allocation strategies for token and compute expenditures.

• Act as a technical escalation point for embedded AI service delivery.

• Remove obstacles for teams, review designs, and establish best practices.

• Work alongside Security teams on threat modeling and controls related to prompt injection, data exfiltration, and over-privileged tools.

• Mentor engineers, conduct design reviews and RFCs, and represent the AI Platform in broad engineering technical decisions.

• Engage in on-call rotations and incident response for production AI services.

⛳️ Requirements

• Over 8 years of experience in software, platform, infrastructure, or SRE engineering.

• Background at the Staff/Principal level or in a tech lead role, with responsibility for architectural ownership across teams.

• In-depth knowledge of LLM and API principles, including context windows, tool utilization, structured outputs, streaming, prompt caching, and variations in provider APIs.

• Practical experience in designing or managing an LLM gateway or a comparable layer, including making build-vs-buy decisions.

• Familiarity with agent orchestration methodologies, including multi-agent workflows, delegation, human-in-the-loop approval processes, memory and context management, and token optimization.

• Experience collaborating with Security teams on threat modeling, security assessments, and risk acceptance for production environments.

• Proficient understanding of the Model Context Protocol (MCP), including server implementation, tool scoping, and reviewing third-party servers for security compliance.

• Hands-on experience with containerization and isolation technologies, such as Docker and Kubernetes.

• Experience with Infrastructure as Code using Terraform or a similar tool in at least one major cloud environment; Azure is preferred.

• Strong understanding of observability practices, including OpenTelemetry, Prometheus, and Grafana, along with reliability engineering for non-deterministic AI systems.

• Excellent coding abilities.

• Proven track record of influencing without authority, authoring RFCs and architecture decision records, achieving team consensus, and articulating 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 the EU AI Act, NIST AI RMF, and ISO/IEC 42001.

• Nice to have: experience with AI coding agents and extension models.

• Nice to have: practical experience in designing or assessing model routing solutions.

• Nice to have: experience in supporting self-hosted or on-premise models.

• Nice to have: experience in developing developer platforms, golden paths, or internal developer portals.

🏝️ Benefits

• Competitive annual salary.

• Private health insurance.

• Flexible benefits plan that allows employees to customize part of their compensation package to meet personal needs.

• Annual bonus based on individual performance and company outcomes.

• Flexible working hours.

• Options for remote work.