AI Engineer/Developer

Il y a 23 heures

Arrondissement of BrusselsCapital, Brussels, Belgique Phoenix Technologies Temps plein
h3Role: AI Engineer/Developer /h3 h3Location: Brussels BE /h3 h3Language: French OR Dutch /h3 pbThe AI Platform runs on a hybrid operating model: managed Azure services (Microsoft Foundry with the OpenAI model family for LLM and embeddings, Azure AI Search, Azure API Management, Azure AI Content Safety) combined with self-hosted open-source components on AKS (agent orchestration in Python with LangChain, ingestion pipeline), with MLflow on Databricks for evaluation and tracing (OpenTelemetry). The Digital Innovation / AI CoE team owns Infrastructure-as-Code for all application-scoped Azure resources, using Terraform and Azure DevOps pipelines. /b /p h3What you will deliver /h3 pbActivities will vary from service to service. Typically you will: /b /p ul liboperate the AI services in production: monitor availability, latency and errors, handle incidents and service requests, analyse root causes, then fix or upscale ; /b /li libkeep answer quality under control: run and maintain evaluation sets (golden sets) with business content owners, track answer quality, non-answer rate and user feedback, and detect and investigate quality regressions ; /b /li liboperate the ingestion pipelines: incremental refresh, failed documents, index health, and onboarding of new content sources or business domains within existing connectors ; /b /li liboperate agent integrations: monitor tool and integration calls to business systems, handle failures and timeouts, and review action logs and exceptions for agents that act on users' behalf ; /b /li libmanage change safely: model version upgrades and retirements, prompt and configuration changes, dependency and security updates, each validated against the evaluation sets before release ; /b /li libfollow run cost: token consumption and cost per service, alerting on drift and proposing optimisations ; /b /li libmaintain the Terraform, Helm and Azure DevOps artefacts, and keep the DEV, TST, ACC and PROD environments consistent ; /b /li libapply data protection rules: trace retention, erasure and access restrictions, as defined in each service's data protection impact assessment ; /b /li libmaintain runbooks and documentation, and report service health to service owners and the AI CoE on a regular basis ; /b /li libdeliver small enhancements and fixes; structural changes and new features stay with the Build team. /b /li /ul