Function
1. Context and Objective
The assignment is aimed at strengthening the AI Platform Team in the implementation,
industrialisation and operational support of a standardised, secure, scalable and cost-
efficient enterprise AI platform.
The AI Platform Engineer is responsible for the hands-on implementation of reusable
platform services for Generative AI, Retrieval Augmented Generation (RAG) and Agentic AI.
The role translates defined architecture, standards and governance requirements into
automated platform components that can be consumed by multiple development and
platform teams.
The focus is on generic platform capabilities, self-service, technical quality assurance and
the controlled transition from proof of concept to production.
2. Key Responsibilities
AI Platform Engineering
• Implement, configure and maintain enterprise AI platform services, with AWS
Bedrock as the primary platform.
• Integrate and manage approved foundation models, model endpoints, inference
services, runtimes and supporting frameworks.
• Develop standardised APIs, SDKs, templates and reference implementations.
• Contribute to lifecycle management, versioning, compatibility and technical
documentation.
Agentic AI & Integrations
• Develop reusable patterns for AI agents, tool use, planning and execution flows.
• Implement and secure MCP servers and other standardised tool/service integrations.
• Develop agent templates covering identity propagation, authorisation, error
handling, time-outs and audit logging.
• Perform technical testing of agent reliability, security and predictability.
RAG Platform Services
• Implement generic retrieval and knowledge services for RAG applications.
• Integrate vector databases, knowledge bases, embedding services and retrieval
components.
• Provide standardised interfaces for document and data access, respecting access
rights and data classification.
• Collaborate with data engineers on data and knowledge pipelines.
DevOps, Automation & Self-Service
• Automate provisioning, configuration, deployment, testing and rollback
using Infrastructure as Code and CI/CD.
• Develop and maintain Terraform modules and GitHub Actions workflows.
• Provide paved-road workflows and self-service capabilities for onboarding teams and
use cases.
• Integrate policy and quality controls into delivery pipelines.
Security, Privacy & Governance
• Implement technical guardrails for prompt/output control, sandboxing, networking,
data access and tool usage.
• Apply secrets management, key management, least privilege and encryption.
• Implement policy-as-code, pre-deployment checks, audit logging and traceability.
• Support security, privacy and compliance assessments and remediation.
Observability, Operations & FinOps
• Set up monitoring and tracing for model calls, agent actions, tool calls, errors, latency
and platform availability.
• Work with Dynatrace, OpenTelemetry, Langfuse and other AI observability solutions
where applicable.
• Support incident, problem and change management, including root cause analysis.
• Monitor and optimise AI platform and infrastructure costs.
3. Required Technical Expertise
• Strong experience in cloud and platform engineering within enterprise
environments.
• Strong practical knowledge of AWS and experience with Amazon Bedrock or
comparable GenAI platforms.
• Strong Python programming skills and experience with API/SDK development.
• Experience with Generative AI, LLMs, RAG, embeddings, vector search and Agentic
AI.
• Experience with MCP, tool integrations or comparable standards is highly desirable.
• Experience with Terraform, GitHub Actions, CI/CD, GitOps and automated quality
controls.
• Knowledge of containers, Kubernetes and preferably Amazon EKS.
• Knowledge of IAM, secrets management, policy-as-code, logging, monitoring and
OpenTelemetry.
• Experience with Dynatrace, Langfuse, OpenSearch, LangGraph or LangChain is a
plus.
4. Required Competencies
• Takes technical ownership and works independently within defined architecture and
governance frameworks.
• Analytical and pragmatic problem-solving approach, with focus on reliability, security
and time-to-value.
• Strong collaboration skills in multidisciplinary teams.
• Enablement-oriented mindset, focusing on reusable solutions rather than team-
specific customisation.
• Able to clearly document and communicate technical decisions, risks and
dependencies.
• Good communication skills in Dutch and English; French is a plus.
5. Desired Profile
• Minimum 5 years of relevant experience in cloud engineering, platform engineering,
DevOps or a comparable technical domain.
• Proven experience building or managing production-ready shared platform services.
• Proven experience with Generative AI or AI/ML in production.
• Experience with hybrid or multi-cloud environments and collaboration with
architecture, security and compliance teams.
• Experience with Agile/Scrum and incident, change and problem management.
• AWS, Kubernetes, security or AI certifications are a plus.
6. Expected Deliverables
• Production-ready and documented AI platform components, APIs, SDKs and
deployment templates.
• Automated provisioning and delivery processes with integrated quality and policy
controls.
• Operational monitoring, tracing, dashboards, alerts and runbooks.
• Reusable patterns for agents, MCP integrations, RAG and model consumption.
• Technical documentation, knowledge transfer and enablement of consuming teams.
• Measurable improvements in reliability, security, self-service and cost efficiency.
7. Collaboration & Reporting
The AI Platform Engineer works under the functional direction of the responsible platform
team lead and reports progress, risks, dependencies and results to the Service Delivery
Manager.
The role involves close collaboration with architecture, security, privacy, cloud, data and
development teams.