MLOps Engineer - Remote

Overview

The MLOps Engineer will be responsible for building and operating scalable, secure infrastructure for Large Language Models (LLMs) at Cognigy, supporting various teams in deploying and maintaining production-grade AI workloads.

In Short

• Design and maintain scalable LLM-serving systems using Kubernetes and KubeRay.
• Automate deployments, rollbacks, and scaling of LLMs.
• Ensure robust monitoring, logging, and alerting for LLM operations.
• Empower ML and product engineers with self-service pipelines.
• Enforce secure deployments and compliance practices.
• Create and maintain technical documentation.
• Evaluate and integrate the latest MLOps technologies.
• Eliminate repetitive tasks to improve operational efficiency.

Requirements

• Hands-on experience running production ML or LLM workloads in Kubernetes.
• Familiarity with distributed ML frameworks such as KubeRay.
• Deep understanding of Kubernetes internals.
• Proficiency with CI/CD systems for ML models.
• Strong experience with cloud platforms (AWS, GCP, Azure).
• Skilled in monitoring and observability for ML workloads.
• Passion for automation and performance tuning.
• Clear communicator and proactive team player.
• MLOps or DevOps certifications (nice to have).

Benefits

• Attractive and performance-oriented salary.
• Company Pension Scheme.
• 25 days paid leave, plus 5 floating days.
• Flexible working options.
• Colleague recognition and celebration events.
• Global Employee Assistance Program.
• Ongoing learning and development opportunities.
• One paid ‘Giving Back Day' each year.
• Subscription to the Calm app for wellness.