AI DevOps Engineer

About the role

VegaNext builds and operates production AI systems, including real‑time AI agents that manage multi‑step conversations. As an AI DevOps Engineer you will ensure the reliability of these agents while maintaining the underlying infrastructure, pipelines, and cloud operations.

Key responsibilities

• Develop and test AI agent behavior, prompts, conversation flows, and tool calling.
• Build replay tests for realistic conversations and investigate logs to diagnose failures.
• Maintain CI/CD pipelines for service deployment and manage cloud resources (provisioning, scaling, cost, security).
• Write infrastructure‑as‑code (Terraform, CloudFormation, etc.), containerize services, and oversee orchestration.
• Set up monitoring, logging, and alerting; support incident response and automate manual operational tasks.

Required profile

• Strong Python programming skills and ability to navigate unfamiliar codebases.
• Hands‑on experience with CI/CD tools such as GitHub Actions, GitLab CI, or Jenkins.
• Working knowledge of cloud platforms (AWS, GCP, or Azure) and containerization with Docker.
• Comfortable with SQL, REST APIs, Git, and software testing.
• Excellent debugging and problem‑solving abilities across application and infrastructure layers.

Required skills

• Python
• CI/CD pipelines (GitHub Actions, GitLab CI, Jenkins)
• Cloud platforms (AWS, GCP, Azure)
• Docker
• SQL
• REST APIs
• Git
• Infrastructure as code (Terraform, CloudFormation, Pulumi)
• LLM APIs (prompting, function calling)
• LiveKit, Twilio, STT, TTS, WebRTC
• Kubernetes or other orchestration
• Monitoring tools (Prometheus, Grafana, Datadog)