For a Client we are looking for a LLM Ops Engineer:
Start: Asap
Long Term
Full-Time
Location: Mechelen + Remote
As a Medior LLM Ops Engineer, you will:
Design AI Systems: Collaborate with AI translators and AI Engineers to design and architect scalable, reliable AI systems on Microsoft Azure. Define and manage cloud environments, infrastructure-as-code, and deployment architectures that support the full LLM lifecycle.
LLMOps Implementation: Adopt best LLMOps practices by setting up CI/CD pipelines for building, testing, and deploying LLMs, including GPT-based systems. Monitor and evaluate model output quality in production, tracking performance degradation, hallucinations, and drift to ensure reliable and consistent results.
Cloud Infrastructure & Optimization: Set up, configure, and manage cloud infrastructure on Microsoft Azure, including provisioning resources, managing environments, and optimizing token usage, latency, and costs.
Networking & Security Infrastructure: Design and manage secure cloud networking on Microsoft Azure, including virtual networks, private endpoints, managed identities, and role-based access control. Ensure AI systems are deployed in compliant, secure environments following zero-trust principles and organizational security policies.
Ensure Security and Ethics: Prioritize security, privacy, and ethics in all AI solutions, ensuring compliance with best practices and regulations.