Staff AI Platform Engineer

Location: Spain (Remote)

Company

hirify.global builds software that supports high-stakes, time-sensitive decisions for wildfire and natural-hazard management, with AI as a core part of its products.

What you will do

• Own the architecture, technical vision, standards, documentation, and technical direction of the AI platform.
• Lead the AI gateway and model-routing strategy, including provider compatibility, hybrid and on-premise routing, failover, caching, rate limits, and build-versus-buy decisions.
• Design agent orchestration, sandboxing, lifecycle management, multi-agent workflows, and human-in-the-loop approval patterns.
• Define identity, access control, governance, MCP registry, skills, plugins, allowlists, audit trails, and security controls for AI systems and agents.
• Standardize evaluation, tracing, observability, drift detection, reliability practices, and FinOps attribution for token and compute usage.
• Act as a technical escalation point, mentor engineers, lead design reviews and RFCs, collaborate with Security, Legal, engineering, and business teams, and participate in on-call and incident response.

Requirements

• 8+ years of experience in software, platform, infrastructure, or SRE engineering, including Staff/Principal-level or tech-lead experience 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, such as Azure API Management, AI Gateway, LiteLLM, Portkey, OpenRouter, Bifrost, or TrueFoundry, including build-versus-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, ideally including AI or agent-based workloads.
• Working knowledge of the Model Context Protocol, including implementing servers, scoping tools, and reviewing third-party servers for security.
• Production experience with containers and isolation using Docker and Kubernetes.
• Infrastructure as code experience with Terraform or similar on at least one major cloud, ideally Azure.
• Solid knowledge of observability and reliability engineering, including OpenTelemetry, Prometheus, and Grafana, and their application to non-deterministic AI systems; strong coding skills; and experience influencing without authority through RFCs, architecture decision records, consensus-building, and communication of technical trade-offs.

Nice to have

• Experience with AI evaluation and observability tools such as Langfuse, Arize Phoenix, Braintrust, Helicone, or Grafana AI Observability.
• FinOps experience with usage-based cost models, tagging, chargeback/showback, budgets, and anomaly detection.
• Familiarity with AI governance frameworks including the EU AI Act, NIST AI RMF, or ISO/IEC 42001, and experience partnering with Legal or Compliance.
• Experience with AI coding agents and extension models such as Claude Code skills, plugins, hooks, or subagents.
• Hands-on experience designing or evaluating model-routing solutions, including fallback, load balancing, and cost- or quality-based routing.
• Experience serving self-hosted or on-premise models using vLLM, Triton, KServe, or similar technologies.
• Experience building developer platforms, golden paths, or internal developer portals such as Backstage.

Culture & Benefits

• Remote work options and flexible working hours.
• Private health insurance and a flexible benefits plan.
• Competitive annual salary and an annual bonus based on individual performance and company results.
• Inclusive environment that values diverse experiences, skills, and career paths.