Senior DevOps Engineer (Cloud Infrastructure, CI/CD, LLMOps)

Architect and optimize cloud infrastructure and CI/CD systems for AI workloads.

Our client is a global technology company specializing in cloud infrastructure, AI operations, and enterprise technology solutions. Supporting organizations worldwide, the company delivers secure, scalable, and reliable cloud environments, helping businesses optimize infrastructure and accelerate AI adoption.

We are looking for a Senior DevOps Engineer to architect, optimize, and own complex cloud infrastructure and CI/CD systems, including MLOps pipelines supporting AI/ML workloads. In this role, you will drive technical decisions, design highly available and cost-efficient architectures, and ensure the security, reliability, and performance of infrastructure across multiple services.

You will lead infrastructure design reviews, mentor engineers, and collaborate with cross-functional stakeholders to translate business requirements into technical solutions. You will also lead incident response and root-cause analysis for critical infrastructure issues, implement monitoring for AI workloads, and strengthen security controls for AI endpoints and agentic systems. Participation in an on-call rotation for after-hours and weekend support is expected.

Required Skills

• 6+ years of experience in technology, with significant ownership of cloud infrastructure and DevOps systems.
• 4+ years of hands-on experience designing, implementing, and optimizing cloud infrastructure and CI/CD pipelines.
• Advanced expertise in cloud platforms, containerization, orchestration, and Infrastructure as Code (IaC).
• Strong experience architecting highly available, scalable, secure, and cost-optimized infrastructure.
• Experience designing and maintaining CI/CD pipelines for distributed applications and AI/ML workloads.
• Understanding of LLMOps principles, including AI model deployment, monitoring, and operational performance.
• Knowledge of AI infrastructure observability, including latency, token costs, model drift, and alerting.
• Experience implementing infrastructure security, compliance controls, and secure deployment practices.
• Understanding of security risks associated with AI endpoints, including prompt injection and data leakage.
• Experience leading technical design reviews, mentoring engineers, and collaborating with cross-functional teams.
• Strong incident management, troubleshooting, and root-cause analysis skills.
• Bachelor's degree in Computer Science, Software Engineering, or a related field, or equivalent practical experience.

Bonus Skills

• Professional-level cloud certification (AWS, Azure, or Google Cloud).
• Experience operating LLMOps infrastructure at scale, including GPU provisioning and vector database hosting.
• Experience securing agentic AI systems and AI-powered applications.
• Experience establishing infrastructure standards and contributing to technical roadmaps.

Skills: DevOps