Course: AI Reliability Engineering
Mentor: Denys Vasyliev, Principal Site Reliability Engineer / UK Global Talent Visa Holder, 17+ years in the industry.
How to apply SRE practices to the new reality of artificial intelligence?
The modern role of DevOps/SRE goes beyond classic pipelines and monitoring. Today, it is critically important to be able to reliably build, scale and automate infrastructure for AI systems – this is no longer the future, but a current market requirement.
Master Kubernetes, modern SRE approaches and AI Reliability Engineering in 9 intensive classes!
Mentor: Denys Vasyliev, Principal Site Reliability Engineer / UK Global Talent Visa Holder, 17+ years in the industry.
- In this course you will:
- Get practical skills that "sell" in interviews and in real projects
- Understand GitOps/GitlessOps and Agentic AI patterns Hands-on with a current toolset
- Create a Kubernetes cluster from scratch
- Understand Control Plane, Controllers, Operators and master infrastructure management as Code.
- Practice with AI Gateways: rate limiting, semantic caching, authorization
- Instrument the application for tracing the distribution of model responses and MCP
- Implement AI agents in Kubernetes
- Learn to work with MCP/A2A, Kagent, AgentGateway, ADK and integrate Agentic AI into production environments
- Get acquainted with AI Observability and Continuous Evaluation practices through OpenTelemetry and Open Inference
- Learn to define AI-oriented SLO/SLA - TTFT (Time To First Token) and TPOT (Time Per Output Token)
It is worth preparing: it will not be easy, because the course is full of practical tasks, work with real infrastructure scenarios and new approaches such as GitLess Ops and Agentic AI. This is not just school theory - you will have to configure, automate and solve complex cases close to the production level.
-
Course result:
- Practical skills in working with Kubernetes.
- Understanding modern DevOps/SRE processes.
- Experience implementing AI agents in a cluster.
Format:
- Collaboration: in teams and pairs
- Mode: online and offline - like a real project
- Activities: lectures, meetings, practical and homework
Duration: three weeks of online classes on Mondays, Wednesdays and Fridays.
Dates: 11.03 - 30.03, 18:30 - 20:30, (Kyiv time, GMT+3), duration of each class ~2 hours.
Platform: Zoom. You will receive a link to the broadcast before the course starts, and it will also be available on this landing page. In addition, all materials and lecture recordings will be available on the learning platform.
-
Interaction:
The number of participants is limited
Event language: Ukrainian
Presentation language: Ukrainian and English
*To perform practical tasks, it is recommended to have basic knowledge of Linux and any programming language.
**We work with Github, so it is recommended to have an account on Github.
Who will be interested?
- Developers
- QA engineers
- System administrators and switchers
- DevOps/SRE approaches
- Everyone who wants to use Kubernetes in their projects
Program
- Building a Real Agentic AI Project from Scratch: SDLC, Infrastructure, Network, Security, Frameworks, LLM, MCP, Agents, Observability and Monitoring
Stack
- MCP/Agents Serving Challenges: agentgateway, kagent, llm-d
- AI SDLC Flow, Tests and Evals: kmcp, Arize Phoenix, Open Inference Evaluators
- Security and Compliance Practices: Prompt guards, LLM Providers Auth, MCP Auth
- Agentic Observability Gaps: MCP/Agent/LLM/Accelerators Monitoring and Tracing
Plan
- K8S DIY: we create and configure containerization, Kubernetes clusters ourselves and controllers
- Git/GitLess Ops (new!): learn and apply modern DevOps/SRE practices
- K8S Agentic AI (new!): learn and build your own agents with Agentic AI frameworks and configure the MCP/A2A stack in Kubernetes
The course concept and all course materials are the intellectual property of FWDAYS. Copying of course content and materials is possible only with the consent of FWDAYS.
Mentor: Denys Vasyliev, Principal Site Reliability Engineer / UK Global Talent Visa Holder
— 17+ years in the industry: from engineer to CTO
— Certified Kubernetes Administrator
— Speaker: Fwdays, DevOpsdays, DevOps-DEX London, SRE Day, Platform Engineering Con
— Author of Kubernetes DIY course
— Author and host of Telegram and YouTube channel "Incorrect DevOps"
Event price
Access to 9 online broadcasts (18 hours)
Presentation and materials
Access to the course recording on the learning platform (1 year)
Access to the chat in the TG, where the speaker will answer questions (1 month)
Participant certificate (subject to homework completion)
Free month in Fwdays Club for those who receive a certificate
Course participants receive a 10% discount on participation in Fwdays conferences
Available payment by installments from Monobank and purchase by installments from PrivatbankIf after the first lesson you realize that your expectations do not match, we will refund your money in full.