AI Platform Engineer
Romania • Full-time
Posted 8d ago
Job Location
Romania
Also open in Portugal, Spain, Italy, Switzerland, France, UK, Ireland, Netherlands, Germany, South Africa
Tech Stack
Remote Work Policy
On-site
Employment Type
Full-time
Categories
AI Agent Engineer
About the job
We are seeking an AI Platform Engineer to build and evolve our organization's AI platform, empowering business teams to deploy reliable, secure, and increasingly autonomous agents. This role involves productionizing AI workflows, building and managing Model Context Protocol (MCP) servers, and developing multi-step agents capable of planning and executing tasks across various tools. You will also be responsible for implementing platform-wide security and governance guardrails, creating robust evaluation frameworks to measure agent quality, and improving observability through tracing, logging, and metrics.
Additionally, you will manage AI expenditure across providers, support internal stakeholders by understanding their needs and developing features, and create reusable AI capabilities like shared skills and plugins. The role also focuses on driving process automation by identifying and implementing AI-driven solutions for repetitive manual workflows and taking end-to-end ownership of projects from technical specification to post-deployment monitoring and improvement.
Responsibilities
- Productionize AI workflows into robust systems with SLAs for use cases like specification-to-pull-request agents and AI-powered code reviews.
- Build, deploy, secure, and maintain MCP servers with authentication, OAuth, and integrations with tools like Slack and GitHub.
- Develop multi-step agents capable of planning and taking action across different tools, progressing through trust stages.
- Implement platform-wide security and governance, including agent identities, scoped credentials, audit logs, and least-privilege access.
- Create evaluation frameworks with test datasets, criteria, and live production scoring systems to measure agent quality.
- Instrument agents and workflows with tracing, logging, cost metrics, drift detection, alerts, and dashboards.
- Track and manage AI usage and spending across providers, establishing budgets and alerts.
- Support internal stakeholders by understanding needs, developing features, creating documentation, and delivering enablement sessions.
- Develop and maintain shared skills, plugins, and knowledge resources for company processes and standards.
- Identify and implement AI automation for repetitive manual workflows, measuring impact and continuously improving.
- Write technical specifications, plan and deliver projects independently, and monitor solutions post-deployment.
Requirements
- At least 5 years of experience as a software, platform, or infrastructure engineer with strong system design, data modeling, testing, and debugging skills.
- 6-12 months of experience shipping LLM-based systems to production and supporting agentic workflows.
- Daily, hands-on experience using AI coding agents like Claude Code and Codex for production code.
- Experience developing autonomous or multi-step agents with tool integrations using frameworks like Claude Agent SDK or Anthropic/OpenAI APIs.
- Practical experience building MCP servers, including OAuth authentication and scoped tokens.
- Knowledge of identity and access management systems (e.g., Okta) and SSO protocols (SAML/OIDC).
- Experience creating automated system identities (e.g., GitHub Apps, service accounts) and managing secrets.
- Understanding of security guardrails and governance practices like least-privilege access and policy-as-code.
- Experience designing evaluation systems for LLM applications, including test sets and production scoring.
- Practical experience implementing production observability using tools like OpenTelemetry, Grafana, or Datadog.
- Experience monitoring and controlling AI expenditure across providers.
- Strong programming skills in TypeScript, Python, or Go, with working knowledge of CI/CD pipelines and cloud infrastructure.
- Demonstrated ability to independently identify and automate manual processes with concrete examples.
- Strong written communication skills for technical specifications and RFCs.
- Ability to understand stakeholder needs, translate ambiguous requests, and explain complex concepts.
- Proactive and autonomous working style with effective prioritization and cross-time zone communication.
- Strong sense of ownership, including validating solutions, monitoring performance, and iterating.
