Senior ML Engineer (AI LLM MLOps Platform)

Xcede are proud to partner with a global energy and sustainability business operating across 20 countries with over 6000 employees and €1+ billion in revenue. Their products and services are used across 14 million homes and commercial properties worldwide. The business is now actively scaling its AI engineering function and building out the platform that will run its production AI systems at scale.

The Role

You will join the AI platform engineering team responsible for the infrastructure that powers the company's AI agents and LLM applications. Your focus is deployment, reliability, observability, and cost, making sure models (both managed and self-hosted) run in production safely, predictably, and efficiently. You will set the operational standards the wider AI engineering function builds on.

What You Will Be Doing

• Building and operating the deployment infrastructure for LLMs, supporting both managed and self-hosted models

• Managing cloud environments through infrastructure-as-code with Terraform

• Containerisation and orchestration with Kubernetes

• Owning observability, monitoring, logging, and model and data drift detection across production systems

• Advising on model selection, performance, and operational cost optimisation

• Establishing production standards: versioning, rollbacks, compliance, and security

• Working closely with AI engineers to move prototypes and models into stable, scalable production

What We Are Looking For

• Senior LLMOps or MLOps experience operating ML and LLM systems in production

• Strong infrastructure-as-code skills with Terraform

• Kubernetes and container orchestration experience

• Cloud experience, ideally Azure (AWS or GCP also relevant)

• Solid Python and software engineering best practices (CI/CD, testing, code quality)

• A production mindset around monitoring, cost, governance, and reliability

• Java exposure is a plus, not a requirement

• Minimum C1 German with strong English essential

Details

• 30 days holiday per year

• Hybrid working with up to 50% remote

• Strong learning and development culture with ongoing training opportunities

• Agile working environment within a globally established business

Interested? Reach out directly to Norman Cistovas at Xcede or apply below.