Senior AI Deployment Engineer
J
JobgetherAI deployment
Based in BrazilFull-TimeSenior
Salary not disclosed
Apply NowOpens the employer's application page
Job Details
- Required Skills
- KubernetesCI/CDDevOpsTerraform
Requirements
- Strong experience or technical expertise in LLMOps, including deployment and operation of large language models and AI-powered systems.
- Knowledge of DevOps practices, including infrastructure automation, deployment management, and CI/CD.
- Understanding of Site Reliability Engineering (SRE), production reliability, availability, performance, and scalability.
- Experience or knowledge of AI security, access control, and production data protection.
- Familiarity with observability and monitoring practices for application and AI systems.
- Understanding of AI FinOps, inference cost management, and cost optimization techniques.
- Knowledge of infrastructure guardrails, AI safety, and risk mitigation for AI models and agents.
- Understanding of model routing and selection strategies for performance and cost optimization.
- Ability to manage production environments, release processes, versioning, and incident recovery.
- Strong problem-solving and collaboration skills, including communicating operational findings and working with AI engineering and delivery teams.
- Knowledge of cloud computing concepts and architectures is nice to have.
- Practical experience with Infrastructure as Code (IaC), particularly Terraform, is nice to have.
- Familiarity with Azure Container Apps, Kubernetes, container-based infrastructure, distributed environments, code reviews, and software quality practices is nice to have.
Responsibilities
- Design and manage CI/CD pipelines for agentic environments.
- Deploy conventional applications across platforms and distribution channels, including app stores, CDNs, mobile release trains, feature flags, and blue/green rollouts.
- Provision, automate, and maintain development, staging, and production environments.
- Operate model and AI agent serving infrastructure to support availability, performance, low latency, and scalability.
- Establish quality, security, and compliance gates throughout delivery pipelines.
- Define versioning strategies, release schedules, rollback procedures, and production recovery processes.
- Implement observability and monitoring for AI solution behavior, operational health, quality, performance, and token consumption.
- Monitor and optimize inference costs, manage budgets, and implement model routing to balance cost and performance.
- Secure production environments with access controls and data protection measures, and implement guardrails to manage model risk and unsafe agent behavior.
- Share production insights on costs, failures, and performance with upstream engineering teams.
View Full Description & ApplyYou'll be redirected to the employer's site
