Team: Engineering / AI SRE Team · Reports to: CTO / AI Lead Format: Working Student (16–20h/week) or Internship (3–6 months)

Automate the "middle of the night" - Build the future of AI-driven SRE

At ilert, we are building the next generation of incident management. We aren't just sending alerts; we are building Autonomous AI SRE Agents that can investigate, analyze, and mitigate production issues before a human even wakes up.

We are looking for an AI Product Engineer (Working Student or Intern) who is excited about the intersection of Generative AI and DevOps. This is not a research role in a vacuum - you will be shipping agentic AI features that interact with real-world infrastructure like Kubernetes, GitHub, and AWS.

Tasks

• Agent Development: Assist in designing agent reasoning loops, prompt templates, and safety constraints for our AI SRE agents.
• Tool Integration: Help build "skills" for our agents, allowing them to interact with real-world tools like Grafana, Prometheus, Kubernetes, and Cloud APIs.
• End-to-End Features: Work with our engineering team to translate complex SRE workflows into intuitive, AI-powered product features.
• Reliability & Safety: Help build "guardrails" and validation layers (using schemas like Zod or JSON schema) to ensure our AI agents act safely and deterministically.
• Evaluation & Testing: Assist in building evaluation suites and test harnesses to measure how well our agents solve real-world technical incidents.
• Collaboration: Work closely with senior SREs to "encode" their expert knowledge into the AI’s reasoning patterns.

Requirements

• Current Student: Enrolled in Computer Science, Artificial Intelligence, Data Science, or a related technical degree.
• Coding Skills: Strong foundations in Rust or TypeScript/Node.js.
• AI Curiosity: You have experimented with LLMs (OpenAI API, LangChain, Anthropic, etc.) and understand concepts like RAG, prompting, and agentic workflows.
• Systems Interest: You have a basic understanding of (or a strong desire to learn) how modern infrastructure works (APIs, Docker, Cloud services).
• Product Mindset: You don’t just care about the model; you care about how the user interacts with the AI to solve a real problem.
• Language: Fluent English (our working language).

Benefits

• Cutting Edge: Work on "Agentic AI"—one of the most exciting frontiers in software engineering right now.
• Real Responsibility: Your prompts and code will help handle real-world production incidents for thousands of companies.
• Hybrid Freedom: Experience our beautiful office in Cologne Rheinauhafen (3 days/week) and work from home (2 days/week).
• Flexibility: We support your academic success with flexible hours during exam seasons.
• Elite Mentorship: Learn directly from the team building ilert’s AI strategy in a fast-paced, high-growth environment.

We hire for passion and a "builder" mentality. If you have a GitHub repo where you've experimented with LLM agents or a project that connects AI to the real world, we definitely want to see it!

ilert is a SaaS company for alerting, on-call management and status pages and helps companies to operate always-on services and respond faster to incidents.