We are looking for a DevOps & AIOps Intern to build an AI-assisted incident response platform that helps operations teams detect, understand and resolve production issues faster. The goal is to reduce time to resolution by combining observability data with LLM-based root-cause analysis and safe automation.
The project involves building a solution capable of:
- Correlating logs, metrics and traces from production services in one place.
- Detecting incidents and grouping related alerts to reduce noise.
- Suggesting likely root causes with LLM agents, evaluated against past incidents.
- Running automated runbooks with human approval gates before any action.
- Measuring impact on detection time and time to resolution.
This internship provides hands-on experience in observability, LLM agents and DevOps automation.
Technical Skills
- Comfortable with Linux, containers (Docker) and scripting (Python or Bash).
- Basic knowledge of Kubernetes and CI/CD.
- Understanding of monitoring and logging concepts.
- Familiarity with REST APIs.
Tech Stack
- Observability: Prometheus, Grafana, OpenTelemetry, Loki or ELK
- Platform: Docker, Kubernetes
- AI: LLM APIs, LangChain or similar agent frameworks
- Automation: Python, Ansible, GitHub Actions
- Tools: Git, PagerDuty or Opsgenie
