Artificial Intelligence Engineer ( Python)

La Fosse; Brussel Hoofdstad; Sur place; EUR 85 000 - 125 000; Plein temps

Résumé du poste

La Fosse in Brussels is seeking a senior AI/ML engineer to own end-to-end data and AI workflows. You will design and optimize Python/SQL pipelines, implement RAG and hybrid search solutions, and orchestrate complex LLM workloads.

You will work with LangChain, LangGraph, and other frameworks to build production-grade AI systems, ensure reliability, scalability, and cost efficiency across AWS/Azure/GCP environments.

Qualifications

• Advanced Python and SQL proficiency with production queries and large-scale data joins.
• Experience with at least two Generative AI components: RAG, hybrid search, and result re-ranking.
• Agentic AI workflows using frameworks like LangGraph, CrewAI, AutoGen, or similar orchestration platforms.
• Model fine-tuning and PEFT techniques (LoRA, QLoRA) for open-source and proprietary models.
• Deployment and management of vector databases (Pinecone, Weaviate, FAISS, etc.) in production.
• Experience with LLM orchestration frameworks (LangChain, LlamaIndex, Semantic Kernel).
• Strong ML foundation: feature engineering, model selection, experimentation and evaluation.
• Cloud engineering across AWS, Azure, or GCP with AI/ML workloads (SageMaker, Vertex AI).
• Solid software engineering: testing, version control, modular architecture, and Git workflows.
• MLOps/DevOps tooling: Docker and CI/CD (GitHub Actions, GitLab CI, Azure DevOps).
• Workflow orchestration tools (Airflow, Prefect, Dagster).
• Container orchestration (Kubernetes).
• AI monitoring/observability tools (Langfuse, Arize, MLflow, Weights & Biases).

Connaissances

Python

SQL

Generative AI

RAG

LangChain

LLM orchestration

MLOps

Docker

Kubernetes

Cloud platforms

Outils

LangGraph

LlamaIndex

Semantic Kernel

Weaviate

Pinecone

Qdrant

pgvector

FAISS

Description du poste

Technical Depth

• Advanced proficiency in Python (including typing, packaging, asynchronous programming, and performance optimisation) and SQL, with experience writing and optimising complex production queries, window functions, and large-scale data joins.
• Hands-on experience with at least two key Generative AI components, including:Retrieval-Augmented Generation (RAG) solutions, covering chunking strategies, hybrid search, and result re-ranking.
• Agentic AI workflows using frameworks such as LangGraph, CrewAI, AutoGen, or custom-built orchestration frameworks.
• Model fine-tuning and PEFT techniques, including LoRA and QLoRA, for both open-source and proprietary models.
• Deployment and management of vector databases in production environments, such as Pinecone, Weaviate, Qdrant, pgvector, or FAISS.
• Experience with LLM orchestration frameworks including LangChain, LlamaIndex, Semantic Kernel, or similar technologies.
• Strong foundation in traditional Machine Learning, including feature engineering, model selection, experimentation, and model evaluation.
• Proven cloud engineering experience across AWS, Azure, or GCP, including the deployment, scaling, governance, and cost optimisation of AI/ML workloads using services such as SageMaker, Azure ML, or Vertex AI.
• Solid software engineering practices, including clean coding standards, modular architecture, automated testing (pytest/unittest), version control, and collaborative Git workflows.
• Experience with MLOps and DevOps tooling, including Docker (essential), alongside at least one of the following:CI/CD platforms (GitHub Actions, GitLab CI, Azure DevOps)
• Workflow orchestration tools (Airflow, Prefect, Dagster)
• Container orchestration platforms (Kubernetes)
• Familiarity with AI monitoring and observability tooling such as Langfuse, Arize, MLflow, Weights & Biases, or custom evaluation and logging frameworks to ensure reliability and performance in production environments.