Senior AI Engineer

Keystone Solutions; Brussel Hoofdstad; Remote; EUR 90,000 - 120,000; Full time

Job summary

Keystone Solutions is seeking a Senior AI Engineer to join a client-site consultancy mission, focusing on developing innovative AI services and end-to-end RAG pipelines. You will collaborate with internal teams to transform complex AI projects into operational services.

Key tech includes Azure OpenAI, AKS, LangChain, and Python, with responsibilities spanning ingestion, security, deployment artifacts, and observability. This role offers hands-on, on-site impact across diverse client environments.

Qualifications

• Experience building production AI services on client-site deployments.
• Strong skills with Python, LangChain and LLMs for end-to-end AI pipelines.
• Proficiency with Azure OpenAI Service, AKS and Azure DevOps in complex environments.
• Ability to design scalable RAG architectures and data ingestion pipelines.

Responsibilities

• Deliver the RAG pipeline end-to-end, from retrieval strategy to answer generation.
• Create the ingestion pipeline: connectors to source platforms, chunking, embedding, incremental refresh.
• Implement security trimming and ACL propagation.
• Manage agent orchestration, prompt templates, and guardrails.
• Set up evaluation and tracing: offline evaluation sets, retrieval and answer-quality metrics, end-to-end tracing.
• Produce Terraform, Helm, and Azure DevOps artifacts needed for service deployment and operation.
• Ensure observability and cost control: instrumentation for latency, token consumption, and run cost, plus quality regression detection after model or prompt changes.
• Provide hypercare and early production support: incident analysis, tuning, runbooks, documentation, and handover of the service to the engineer responsible for the Run phase.

Skills

Python

LangChain

LLM

Azure OpenAI Service

Azure DevOps

Azure Kubernetes Service

RAG

Vector databases

Tools

Azure DevOps

Azure Kubernetes Service (AKS)

Azure OpenAI Service

Terraform

LangChain

Vector databases

Job description

Mission Overview

Keystone Solutions is seeking a Senior AI Engineer to join a consultancy mission at a client site, focusing on the development of innovative AI services. This role involves working closely with internal teams to transform complex AI projects into operational services.

Role Responsibilities

• Delivering the RAG pipeline end-to-end, from retrieval strategy to answer generation.
• Creating the ingestion pipeline: connectors to source platforms, chunking, embedding, incremental refresh.
• Implementing security trimming and ACL propagation.
• Managing agent orchestration, prompt templates, and guardrails.
• Setting up evaluation and tracing: offline evaluation sets, retrieval and answer-quality metrics, end-to-end tracing of requests and agent steps.
• Producing Terraform, Helm, and Azure DevOps artifacts needed for service deployment and operation.
• Ensuring observability and cost control: instrumentation for latency, token consumption, and run cost, plus quality regression detection after model or prompt changes.
• Providing hypercare and early production support: incident analysis, tuning, runbooks, documentation, and handover of the service to the engineer responsible for the Run phase.

Why Join Keystone Solutions?

By joining Keystone Solutions, you will experience:

• Consultancy Nature: Engage in on-site work, embodying the consultant identity.
• Dynamic Projects: Tackle a variety of challenges across different client environments.
• Turbo-Charged Learning: Benefit from professional development and broad learning experiences.
• Skyrocketing Ambition: Enjoy a commitment to career growth within our framework.
• Values:

Duration

As soon as possible - 02/11/2026 4 weeks (full time)

Skills required

• Azure DevOps - Level: Advanced - Most recent: This year
• Azure Kubernetes Service - AKS - Level: Advanced - Most recent: This year
• Azure OpenAI Service - Level: Advanced - Most recent: This year
• LangChain - Level: Intermediate - Most recent: Any time
• LLM / Large Language Models - Level: Advanced - Most recent: This year
• Python - Level: Advanced - Most recent: This year
• RAG (Retrieval-Augmented Generation) - Level: Advanced - Most recent: This year
• Terraform - Level: Advanced - Most recent: This year
• Vector databases - Level: Intermediate - Most recent: This year

Language requirements

Dutch or French
Level Native or bilingual proficiency
English
Level Full professional proficiency