Cognigy is seeking a skilled and ambitious MLOps Engineer to join their Engineering team in Düsseldorf or remotely in Germany.
The role involves building and operating scalable, secure infrastructure for Large Language Models (LLMs).
Responsibilities include designing and maintaining LLM-serving systems using Kubernetes and KubeRay, automating deployments, optimizing resource usage, and ensuring robust monitoring and logging for LLM operations.
The MLOps Engineer will support Machine Learning, Product, and SRE teams, enforce security practices, improve documentation, drive innovation by integrating the latest MLOps technologies, and reduce operational toil.
Cognigy emphasizes professional growth, offering opportunities for career development and involvement in high-impact projects.
Requirements:
Candidates must have hands-on experience running production ML or LLM workloads in Kubernetes.
Familiarity with distributed ML frameworks such as KubeRay, Ray Serve, or similar is required.
A deep understanding of Kubernetes internals, especially GPU scheduling, autoscaling, and multi-tenant environments is essential.
Proficiency with CI/CD systems for ML models and versioned deployment strategies is necessary.
Strong experience with cloud platforms (AWS, GCP, or Azure), networking, and security best practices is required.
Candidates should be skilled in monitoring and observability for ML workloads using tools like Prometheus and Grafana.
A passion for automation, performance tuning, and cost optimization for LLM workloads is important.
Clear communication skills and the ability to work as a proactive team player in fast-paced, cross-functional environments are essential.
MLOps or DevOps certifications are considered a plus.
Benefits:
Cognigy offers an attractive and performance-oriented salary.
Employees benefit from a Company Pension Scheme.
The position includes 25 days of paid leave, plus 5 floating days, and public holidays.
There is a unique opportunity to help build and shape the company with minimal hierarchy.
Flexible working options are available to employees.
Cognigy hosts colleague recognition, reward, and celebration events.
Employees have access to a Global Employee Assistance Program.
A ClassPass membership is provided, offering access to various fitness and wellness experiences.
Ongoing learning and development opportunities, including access to Udemy, are available.
Employees receive one paid ‘Giving Back Day' each year to volunteer for a charity or community activity of their choice.
A subscription to the Calm app is provided for employees and five friends or family members, offering guided meditation, sleep stories, music, and masterclasses.
