ilert GmbH is hiring an AI Product Engineer (LLM Agents & SRE Automation) (f/m/x)

Team: Product & Engineering • Reports to the CTO Location: Hybrid - Cologne (Rheinauhafen) - 3 days in office, 2 days remote (Tue and Thu) Transform the landscape of self-directed incident resolution We're committed to eliminating service interruptions. Numerous DevOps and SRE teams depend on ilert to swiftly detect, resolve, and communicate system incidents. As our inaugural AI Solutions Architect, you'll construct the foundation of ilert's AI-driven strategy: intelligent, adaptive agents capable of diagnosing alerts, conducting comprehensive root cause investigations, executing controlled mitigations, and maintaining service stability. This represents a hands-on opportunity to translate operational expertise and product understanding into robust, production-ready AI systems. Tasks Architect & Construct Intelligent Agents - Develop agent reasoning frameworks, prompt strategies, and safety protocols. - Create sophisticated multi-step tool-integrated agents (logs, metrics, traces, k8s, Git, CI/CD, cloud APIs). - Implement autonomous workflows: investigation → analysis → mitigation → validation. Deliver Product Capabilities - Collaborate with product and engineering to develop AI-enhanced features addressing genuine customer challenges. - Convert complex SRE methodologies into intuitive AI-powered user experiences. - Assume full feature ownership (design → prototype → implementation → deployment). Integrate with Operational Ecosystems - Connect language model agents with Grafana, Prometheus, Kubernetes, GitHub, CI/CD, cloud platforms, etc. - Design secure tool schemas and APIs for autonomous execution. Guarantee Reliability, Security & Predictability - Establish protective mechanisms for safe, reversible interventions. - Validate model outputs using structured schemas (e.g., Zod, JSON schema). - Develop comprehensive evaluation frameworks, testing environments, and performance monitoring. Cross-Team Collaboration - Engage with SREs to encode operational knowledge into intelligent agents. - Collaborate with Product to shape requirements and strategic roadmap. - Influence ilert's broader AI strategic direction. Requirements Essential Competencies - Proven experience developing AI-powered applications with large language models - Advanced prompt engineering and agent design capabilities - Demonstrated expertise implementing multi-step tool-integration flows - Robust software engineering foundations (preferably Rust) - Proven API, backend service, and automation integration skills - Capacity to analyze reliability, safety, and controlled automation scenarios - Product-oriented mindset: transforming ambiguous challenges into deliverable solutions Preferred Qualifications - Background in SRE, DevOps, or incident management - Familiarity with observability platforms - Practical Kubernetes expertise - Experience with production agent frameworks Interpersonal Attributes - Passion for creating tangible products - Exceptional communication and analytical thinking - Comfort with high-autonomy, ownership-driven environments - Commitment to reliability and automation Benefits - Pioneer autonomous SRE agent development - Product-focused organizational culture - Flexible hybrid work environment - Minimized meeting culture - High-impact, rapidly deployable work - Senior, agile team structure - Contemporary technological ecosystem - Direct involvement in on-call innovation - Founder-led startup experience Submission Requirement: Include one demonstrative link showcasing AI-powered system expertise.