AI Architect

VBeyond Corporation; Den Haag; On-site; EUR 90,000 - 120,000; Full time

Job summary

VBeyond Corporation is seeking a hands-on AI Architect to design and build enterprise-scale Generative AI systems. This role demands close involvement with the code and guiding teams through real production challenges on Azure and AWS.

The ideal candidate should have strong experience in LLMs, RAG, and prompt engineering, alongside coding and debugging capabilities. You will oversee the complete AI architecture, focusing on deployment and operational excellence.

Qualifications

• Strong hands‑on experience with LLMs, RAG, Agentic AI, and prompt engineering.
• Proven ability to code, debug, and optimize production AI systems.
• Solid experience building GenAI solutions on both Azure and AWS.

Responsibilities

• Design and build enterprise‑grade GenAI solutions for real business use cases.
• Own end‑to‑end AI architecture, from model selection to deployment.
• Deploy and operate GenAI systems on Azure and AWS.

Skills

Experience with LLMs

Prompt engineering

Debugging production AI systems

Building GenAI solutions

Cloud deployment on Azure

Cloud deployment on AWS

Tools

Python

FastAPI

LangChain

LangGraph

MCP

Job description

We are looking for a hands‑on AI Architect who designs and builds enterprise scale Generative AI systems. This is not a conceptual or advisory role. You will stay close to the code, guide low‑level implementation, review pull requests, and help teams solve real production challenges in GenAI systems deployed on Azure and AWS.

What You Will Do

• Actively design and build enterprise‑grade GenAI solutions for real business use cases.
• Own end‑to‑end AI architecture, from model selection and retrieval strategy to APIs, orchestration, and cloud deployment.
• Write code and prototypes using Python, FastAPI, LangChain, LangGraph, and MCP.
• Design and implement RAG pipelines including chunking strategies, embeddings, vector search, and hybrid retrieval.
• Build and guide multi‑agent systems with tool calling, memory/context management, and fallback handling.
• Dive into low‑level technical details to unblock teams (retrieval quality, latency, hallucinations, cost issues).
• Make architecture‑level trade‑offs across accuracy, latency, scalability, reliability, and cost.
• Deploy and operate GenAI systems on Azure and AWS, ensuring scalability, resilience, and cost efficiency.
• Implement observability: logging, tracing, token usage tracking, and performance monitoring.
• Establish hands‑on best practices for prompt versioning, evaluation, testing, and AI quality assurance.
• Implement guardrails and safety controls including content filtering, PII protection, hallucination mitigation, and access control.
• Design secure architectures using OAuth, Azure AD / IAM, RBAC, compliance, and audit logging.
• Review code, document architectural decisions, and mentor engineers by working alongside them.

What You Must Bring

• Strong hands‑on experience with LLMs, RAG, Agentic AI, and prompt engineering.
• Proven ability to code, debug, and optimize production AI systems.
• Solid experience building GenAI solutions on both Azure and AWS (cloud‑agnostic mindset).
• Hands‑on experience with: Deep understanding of distributed systems and cloud‑native architecture.
• Ability to guide teams at implementation level, not just through design documents.