Senior DevOps Engineer - AI/ML Infrastructure

Position Overview:

Key Responsibilities:

• Design and implement CI/CD pipelines for AI applications including model deployment and agent workflows
• Build and maintain Kubernetes clusters optimized for AI workloads including GPU resource management
• Implement comprehensive monitoring and observability for AI systems including custom metrics for model performance
• Develop infrastructure-as-code solutions for scalable AI service deployments
• Establish reliability engineering practices including SLA management and incident response for AI systems
• Optimize cloud infrastructure costs with focus on GPU utilization and LLM API usage
• Implement security and compliance frameworks for AI applications and data pipelines
• Collaborate with development teams to ensure production readiness of AI agents and RAG systems
• Manage multi-cloud deployments and vendor integrations for AI services

Required Qualifications:

• Bachelor's degree in Computer Science, Engineering, or related technical field
• 7-10 years of DevOps/Infrastructure experience with demonstrated production system ownership
• Strong expertise in Kubernetes orchestration and container management (Docker)
• Proficient in Python scripting and automation
• Extensive experience with Linux system administration and performance tuning
• Hands-on experience with Jenkins or similar CI/CD platforms
• Production experience with cloud platforms (AWS, GCP, or Azure)
• Experience with Infrastructure-as-Code tools (Terraform, CloudFormation, or similar)

AI/ML Infrastructure Requirements:

• Experience deploying and managing AI/ML workloads in production environments
• Understanding of RAG system infrastructure requirements and vector database operations
• Knowledge of LLM API integration patterns and rate limiting strategies
• Experience with GPU cluster management and resource optimization
• Familiarity with AI agent workflows and their operational characteristics

Site Reliability Engineering Skills:

• Production monitoring and alerting experience with tools like Prometheus, Grafana, or DataDog
• Incident response and post-mortem experience with complex distributed systems
• Capacity planning and performance optimization for high-traffic applications
• Experience with log aggregation and distributed tracing systems
• Understanding of reliability patterns including circuit breakers and graceful degradation

Preferred Qualifications:

• Experience with MLOps practices and model deployment pipelines
• Knowledge of AI-specific monitoring including model drift detection and performance metrics
• Experience with cost optimization strategies for AI workloads
• Background in financial services, gaming, or other high-availability environments
• Certification in major cloud platforms (AWS Solutions Architect, GCP Professional, etc.)
• Experience with service mesh technologies (Istio, Linkerd)

Technical Environment:

• Multi-cloud infrastructure with primary focus on AWS/GCP
• Kubernetes-based container orchestration
• Modern observability stack with custom AI metrics
• GitOps workflows and infrastructure automation
• Integration with enterprise security and compliance frameworks

  Role & responsibilities

Preferred candidate profile