AI/ML Engineer | Agentic AI & Azure (Production Environment)

Are you an experienced AI/ML Engineer who enjoys building real, production-grade AI systems? We are working with a leading enterprise client on a cutting-edge AI platform, focused on agentic AI, LLM systems, and scalable Azure-based solutions.

This is not about prototypes, this role is all about designing and deploying intelligent AI agents in production environments.

Key Responsibilities

Design and build production-grade AI agents with planning, reasoning, and tool-use capabilities

Architect stateful agent workflows using frameworks like LangGraph or AutoGen

Build and productionize RAG pipelines (data ingestion, embeddings, retrieval optimization, re-ranking)

Integrate LLMs with enterprise systems via APIs, tools, and external data sources

Establish evaluation, observability, and guardrails (accuracy, safety, latency, cost)

Deploy and operate AI applications using Docker, Kubernetes, and Azure

Drive technical decisions and mentor engineers in agentic AI best practices

What You Bring

7–10+ years in software engineering with strong Python skills

Proven experience building agent-based / autonomous AI systems in production

Hands-on experience with OpenAI APIs (incl. function calling & orchestration)

Experience with frameworks such as:

LangChain, LangGraph, AutoGen, CrewAI

Strong knowledge of RAG architectures, vector databases (Pinecone, Weaviate, Azure AI Search)

Experience with LLM evaluation, prompt optimization, and safety techniques

Experience with Docker, Kubernetes, and cloud (Azure preferred)

Familiarity with backend frameworks (e.g. FastAPI) and microservices architecture

Why this role?

Work on next-gen AI systems (agentic AI & LLMs) in a real production setting

High-impact project within a major enterprise environment

Collaborate with top engineers on scalable AI architecture

Hybrid setup in Amsterdam

Interested or want to learn more? Feel free to reach out directly.