Course
LLM platforms hands-on
Site reliability engineering for applied AI
Tick off what you've done and continue on any device. Sign up for free
- Foreword
- Day 0: Build the training ground approx. 60 min
- Day 1: Linux internals approx. 120 min
- Day 2: Network debugging approx. 120 min
- Day 3: Python for SRE – llmctl approx. 150 min
- Day 4: Go for SRE – llm-gateway approx. 180 min
- Day 5: Mistral models on a Linux VM approx. 150 min
- Day 6: Multi-tenant Kubernetes approx. 120 min
- Day 7: Model serving on Kubernetes approx. 150 min
- Day 8: Observability I – metrics approx. 150 min
- Day 9: Observability II – logs and traces approx. 150 min
- Day 10: SLOs, Alerting and On-Call approx. 150 min
- Day 11: Incident Response and Post-Mortem approx. 150 min
- Day 12: Infrastructure as Code approx. 150 min
- Day 13: Security – Secure SDLC and Supply Chain approx. 180 min
- Day 14: Hybrid and On-Prem at the Customer approx. 180 min
- Day 15: Competition – Disaster Drills approx. 240 min
- Appendix A: Cheat Sheet
- Appendix B: Final Exam 180 min hands-on + 30 min questions
- Appendix C: Interview Preparation Applied AI / SRE