MLOps Engineer
Description For MLOps Engineer
Cognigy, a pioneering company in AI-powered customer service solutions, is seeking a skilled MLOps Engineer to join their Engineering team. This role presents an exciting opportunity to work with cutting-edge AI technology and shape the future of customer service automation.
The position involves building and maintaining scalable infrastructure for Large Language Models (LLMs) using modern technologies like Kubernetes and KubeRay. As an MLOps Engineer, you'll be responsible for ensuring the optimal performance, reliability, and security of Cognigy's AI infrastructure while working closely with Machine Learning, Product, and SRE teams.
The role offers a perfect blend of technical challenges and innovation, requiring expertise in Kubernetes, cloud platforms, and MLOps best practices. You'll be working on critical tasks such as automating deployments, optimizing resource usage, implementing robust monitoring systems, and maintaining high security standards for AI workloads.
Cognigy offers an excellent work environment with a strong focus on professional growth and development. The company culture is built on their 4Ts - Team, Trust, Transparency, and Technology. They provide comprehensive benefits including flexible working options, learning opportunities, and various wellness perks.
This position is ideal for someone passionate about AI infrastructure, automation, and operational excellence, offering the chance to work with a global team while making a significant impact in the rapidly evolving field of conversational AI. Whether working remotely or from their Düsseldorf office, you'll be part of a diverse, passionate team that's transforming customer service through innovative AI solutions.
Responsibilities For MLOps Engineer
- Design and maintain scalable LLM-serving systems using Kubernetes and KubeRay
- Automate deployments, rollbacks, and scaling of LLMs while optimizing resource usage and performance
- Ensure robust monitoring, logging, and alerting for LLM operations
- Empower ML and product engineers with self-service pipelines and scalable infrastructure
- Enforce secure deployments, compliance practices, and robust incident response strategies
- Create and maintain technical documentation
- Evaluate, adopt, and integrate the latest MLOps and LLM-serving technologies
- Eliminate repetitive tasks and improve operational efficiency across the platform
Requirements For MLOps Engineer
- Hands-on experience running production ML or LLM workloads in Kubernetes
- Familiarity with distributed ML frameworks such as KubeRay, Ray Serve, or similar
- Deep understanding of Kubernetes internals, especially GPU scheduling, autoscaling, and multi-tenant environments
- Proficiency with CI/CD systems for ML models, and versioned deployment strategies
- Strong experience with cloud platforms (AWS, GCP, or Azure), networking, and security best practices
- Skilled in monitoring and observability for ML workloads
- Passion for automation, performance tuning, and cost optimization for LLM workloads
- Clear communicator and proactive team player
- MLOps or DevOps certifications (nice to have)
Benefits For MLOps Engineer
- Attractive and performance-oriented salary
- Company Pension Scheme
- 25 days paid leave, plus 5 floating days, plus public holidays
- Flexible working options
- Colleague recognition, reward and celebration events
- Global Employee Assistance Program
- ClassPass membership
- Ongoing learning and development opportunities, including Udemy
- One paid 'Giving Back Day' each year
- Subscription to the Calm app for you plus five family members
Jobs Related To Cognigy MLOps Engineer
