Mid-Level Dev(Sec)Ops Engineer – AI Platform / Model Ops

About the role

You ensure platform stability and security, including incident response and troubleshooting. You optimize the performance, scalability and cost-efficiency of the infrastructure. You collaborate closely with MLOps and IT security teams on model deployments. Monitor systems proactively to ensure high availability, detect incidents early and perform root cause analysis

What you'll do

• Monitor systems proactively to ensure high availability, detect incidents early and perform root cause analysis
• Analyze support tickets to identify recurring issues and implement improvements that reduce manual support effort
• Develop and maintain automation scripts and internal applications using Python and Bash to improve efficiency and reduce manual tasks
• Support release and change management activities in line with internal processes and guidelines
• Create and maintain documentation, standard operating procedures, troubleshooting guides and operational guidelines

What you need

• Python
• LLMs
• MLOps
• Incident response
• Root cause analysis
• SOP writing
• Any graduate

Good to have

• Linux
• Kubernetes
• Bash