Job description
We are looking for a Medior AI Engineer to operate AI assistants and agents as they enter production. The services combine RAG with agents that call tools and business systems. You will take over services from the build team and keep them reliable, secure, measurable and cost-efficient as new services go live.
Your role
- Monitor availability, latency and errors, handle incidents and investigate root causes.
- Maintain evaluation sets with content owners and track answer quality, feedback and regressions.
- Operate content ingestion pipelines and monitor agent integrations, failures and action logs.
- Validate model, prompt, configuration and security changes before release.
- Track token consumption and service costs, and propose improvements.
- Maintain , and artefacts across environments.
- Apply data protection rules, maintain runbooks and report service health.
- Deliver small fixes and enhancements alongside engineers, content owners and operations teams.
You have
- 4 to 6 years of experience with , used in the last 12 months.
- 4 to 6 years of experience with , used in the last 12 months.
- 4 to 6 years of experience with OpenAI Service, used in the last 12 months.
- 4 to 6 years of experience with .
- 4 to 6 years of experience with , used in the last 12 months.
- 4 to 6 years of experience with , used in the last 12 months.
- 4 to 6 years of experience with RAG, used in the last 12 months.
- 4 to 6 years of experience with , used in the last 12 months.
- 4 to 6 years of experience with vector databases, used in the last 12 months.
- or at C2 level.
- at C1 level.
A plus
- 4 to 6 years of experience as an AI engineer, including work in the last 12 months.
- Experience with .
- Experience with Foundry.
- Experience with AI Search.
- Experience with Azure .
- Experience with Azure AI Content Safety.
- Experience with .
- Experience with .
- Experience with OpenTelemetry tracing.
- Experience with .
- Experience with .
- Experience in and root cause analysis.
- Experience maintaining LLM evaluation sets and tracking answer quality.
- Experience operating content ingestion pipelines.
- Experience operating AI agent integrations with business systems.
- Experience monitoring AI service costs and token consumption.
Working at Neurho
Founded in 1998, Neurho is a Belgian IT and business consultancy. For more than 25 years, we have been helping banks, insurers, energy companies and public institutions in Belgium and Luxembourg with their transformation projects. At Neurho, you work on varied and challenging assignments, where your expertise is recognised and your growth encouraged. On top of your salary, you enjoy many extra-legal benefits, designed to suit your role, your needs and your personal wishes.
Neurho is committed to equal opportunity and welcomes every application, regardless of age, origin, nationality, gender, social background, beliefs or disability.