Note: The job is a remote job and is open to candidates in USA. Saviance is seeking a skilled DevOps Engineer with a strong interest in Agentic AI and Generative AI systems. In this role, you will design, automate, and manage cloud-native infrastructure that powers AI applications and large-scale data processing workloads, ensuring reliable and secure platforms for deploying AI-powered products.

Responsibilities

• Design, implement, and maintain cloud infrastructure across AWS, Azure, or GCP environments
• Build and manage CI/CD pipelines for rapid and reliable software delivery
• Automate infrastructure provisioning and configuration using Infrastructure as Code (IaC) tools
• Deploy, monitor, and optimize AI/ML and Agentic AI workloads in production environments
• Manage containerized applications using Docker and Kubernetes
• Implement observability solutions including logging, monitoring, alerting, and performance tracking
• Ensure platform reliability, security, scalability, and cost optimization
• Collaborate closely with software engineers, AI engineers, and product teams to streamline deployment workflows
• Support MLOps and LLMOps practices for model deployment, evaluation, and lifecycle management
• Troubleshoot infrastructure, networking, and deployment issues across distributed systems

Skills

• Strong experience in DevOps, Platform Engineering, or Site Reliability Engineering
• Hands-on experience with cloud platforms such as AWS, Azure, or GCP
• Proficiency with Infrastructure as Code tools such as Terraform or CloudFormation
• Experience building and managing CI/CD pipelines
• Strong knowledge of Docker, Kubernetes, and container orchestration
• Proficiency in Python, Shell scripting, or similar automation languages
• Understanding of networking, cloud security, load balancing, DNS, VPNs, and firewalls
• Experience with monitoring and observability tools
• Strong troubleshooting and problem-solving skills
• Ability to thrive in a fast-paced startup environment
• Experience with MLOps and AI infrastructure
• Familiarity with Vertex AI, SageMaker, or similar AI/ML deployment platforms
• Knowledge of Large Language Models (LLMs), Agentic AI systems, and AI orchestration frameworks
• Experience deploying Retrieval-Augmented Generation (RAG) pipelines and AI-powered services
• Familiarity with vector databases, distributed systems, and scalable data platforms
• Exposure to security automation, compliance, and cloud governance practices

Benefits

• Remote-first work environment with flexibility and autonomy
• Collaborative culture focused on innovation, ownership, and continuous learning
• Significant opportunities for technical growth and leadership as AI adoption scales

Company Overview