Senior AI Platform Engineer

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

📋 Description

• Develop and maintain essential AI platform services, which encompass gateway integrations, skills/plugins review pipelines, a curated MCP registry, and tools for cost management and observability.

• Configure, enhance, and manage the AI gateway to facilitate routing, authentication, rate limits, quotas, metadata tagging, and the onboarding of teams and models.

• Create and manage automated validation processes, review gates, versioning, and release workflows for skills and plugins.

• Write and evaluate skills, agents, and plugins.

• Oversee MCP server intake, conduct security reviews, define tool scopes and allowlisting; develop internal MCP servers as necessary.

• Establish cost tagging and attribution for token and compute expenditures, and create dashboards and alerts.

• Instrument AI services and agents with tracing, metrics, and evaluations; monitor latency, errors, quality, and cost per request.

• Configure scoped identities and secrets for agents and automation processes.

• Work in conjunction with Security teams on reviews, incident responses, access scoping, audit logging, and secrets rotation.

• Set up model routing rules, fallbacks, and load balancing among model providers.

• Create golden-path templates, command-line interfaces (CLIs), and documentation; provide support during office hours and engineering workshops.

• Participate in the on-call rotation, address production incidents, and develop fixes and runbooks.

⛳️ Requirements

• A minimum of 5 years in software, platform, DevOps, or SRE engineering, with experience in building and operating production services.

• Hands-on experience with LLM APIs, including tool usage, structured outputs, streaming, and prompt caching.

• Solid understanding of the distinctions between LLM providers, including Anthropic Messages and OpenAI-compatible APIs.

• Experience in integrating or configuring an API or LLM gateway, focusing on routing, authentication, rate limiting, and tagging.

• Practical experience in building with AI coding agents and extension models, including skills, plugins, MCP servers, and hooks.

• Strong programming skills.

• Familiarity with Docker, Kubernetes, and infrastructure as code tools like Terraform on a major cloud platform, preferably Azure.

• Experience with CI/CD practices such as GitLab CI, including automated validation and review processes.

• Experience collaborating with Security teams to implement controls, resolve findings, and support security assessments.

• Knowledge of observability tools like OpenTelemetry, Prometheus, and Grafana.

• Experience in being on call for production systems.

🏝️ Benefits

• Competitive annual salary.

• Private health insurance coverage.

• A flexible benefits plan that allows customization of part of the compensation package to meet personal needs.

• Annual bonus based on individual performance and company results.

• Flexible working hours.

• Options for remote work.