AI Engineer
Sobre el proyecto y el rol
[15:34, 1/10/2026] Flor Hublance Empresa: Summary of the Project / collaboration scope Two MVP’s will be executed for key supporting capabilities—Briefing, Workflow, and Reg Checker—to assess their feasibility, value, and alignment within the future E2E ecosystem Integration to publications platform with enable speedy dissemination. Data connections will enable to measure KPIs for performance and efficiency of process. This role combines hands-on engineering, enablement, and governance—defining how AI is used in software development while actively supporting teams in building their first applications using AI-assisted workflows. Main responsibilities / objectives Design, build, and maintain internal AI tools end-to-end — frontend interfaces, backend services, and AI agent workflows (Azure Foundry–based) leveraging AI to fast-track development. Develop and maintain AI agent orchestration, prompt logic, and model integration pipelines Build and maintain data storage and infrastructure components (e.g., PostgreSQL, Azure App Service) Suggest new innovative patterns to improve the software development process. Establishing and enforcing high standards for code quality, test coverage, and performance by conducting rigorous code reviews Identify common pitfalls and turn them into reusable best practices and guardrails. Implement and maintain the AI development lifecycle: model/agent evaluation, deployment, and monitoring Embed AI into the development lifecycle (IDE, CI/CD, code reviews). Build internal tooling or wrappers to: Standardize usage patterns, Enforce guardrails, Capture metrics and insights Prevent anti-patterns such as: Blindly trusting generated code, Inconsistent architectures, Duplication or technical debt at scale Build QA automation for AI outputs (e.g., LLM-based evaluation pipelines, automated testing of generative behavior) Support identity, access, and security implementation for AI tools (e.g., SSO, Azure AD) Identify technical risks — model drift, latency, token consumption/cost, scalability, data quality — and address them proactively Expected deliverables Working AI agent workflows deployed on Azure Foundry, integrated end-to-end with backend services Full-stack features shipped — frontend interfaces and backend (Node.js) services for internal AI tools, delivered within sprint cycles Data layer implementation — functioning DB schemas/integrations supporting the tools' data needs Infrastructure migrations completed — e.g., successful cloud migrations (such as to Azure App Service) with minimal downtime/disruption QA automation pipelines — functioning LLM-based evaluation and automated testing suites for generative AI outputs, integrated into the development workflow Technical documentation — architecture docs, setup guides, and runbooks for the components they build Sprint deliverables — consistent delivery of committed tasks within Scrum sprint cycles, with clean, tested, production-ready code Risk mitigation reports/fixes — identified and resolved technical issues around model drift, latency, cost (token consumption), and scalability Requested skills 8+ years of software engineering experience, with solid experience as a full-stack developer leveraging AI tools Proven experience building production-grade applications. Hands-on experience using AI coding tools in real projects. UX/UI experience and product design Strong full-stack skills — proficient across frontend (e.g., React/Next.js or similar) and backend (Node.js) stacks Hands-on experience with Azure AI Foundry (agent orchestration, model deployment, evaluation) — required Experience with Azure cloud services: Azure App Service, Foundry, Azure AD Understanding of MLOps basics: model versioning, CI/CD, monitoring Experience building or working with LLM-based QA/evaluation pipelines Strong understanding of: Prompt engineering for c… [15:34, 1/10/2026] Flor Hublance Empresa: Full remote horario CET con ingles