COURSE & TRAINING
ML & AI for DevOps
Use machine learning and AI to improve DevOps workflows through predictive observability, anomaly detection, forecasting, and log intelligence.
Online
CHF 1'250
Live, instructor-led public or private delivery.
On-site
CHF 2'500
On-site delivery for team or public cohorts.
Private team cohort
On request
Private delivery tailored for your engineering team.
Who this training is for
DevOps Engineers
Apply forecasting, anomaly detection, and log intelligence to everyday platform workflows.
SRE Engineers
Use ML-assisted signals to improve incident analysis, reliability scoring, and operational decisions.
Platform Engineers
Explore how AI-enabled tooling can support observability, automation, and internal developer platforms.
What you'll learn
Understand ML use cases in DevOps
Learn where machine learning improves incident prediction, proactive scaling, alerting, and reliability scoring in operational workflows.
Build forecasting and anomaly detection workflows
Work with time series models, anomaly detection techniques, and alerting strategies for system metrics and logs.
Apply NLP to operational data
Use NLP techniques for log classification, grouping similar incidents, and extracting useful context for escalation and root cause analysis.
Deploy AI-enabled observability pipelines
Connect model training, serving, and visualization into practical monitoring and decision-support workflows.
PREREQUISITES
What participants should bring
Participants should be familiar with DevOps practices and tooling, comfortable with Python scripting, and have a basic understanding of system metrics, logs, and monitoring tools. Some exposure to machine learning is a plus.
PREPARATION
Before the course starts
Participants should be ready for hands-on work with ML environments, experiment tracking, forecasting pipelines, API deployment, and log analysis exercises.
CURRICULUM
Inside ML & AI for DevOps
This course is available online, onsite, and as a private team cohort. It can be adapted to a participant's observability stack, operational data, and platform constraints.
Foundations of Machine Learning for DevOps
Day 1
How ML fits into DevOps workflows and how to build the first reliability-oriented prediction pipeline.
Foundations of Machine Learning for DevOps
Day 1
How ML fits into DevOps workflows and how to build the first reliability-oriented prediction pipeline.
Theoretical Part
- DevOps meets ML: where, why, and how
- Observability 2.0 from reactive to predictive
- Architecture of ML-enhanced DevOps platforms
- ML workflow steps from data to model to deployment and monitoring
- Feature engineering for system metrics and logs
Practical Part
- Train and evaluate ML models such as Random Forest and XGBoost for reliability scoring
- Set up ML experiment tracking with MLflow and version control with Git
- Containerize the ML application with Docker
- Interpret model outputs for operational decision-making
Time Series Modeling and Forecasting
Day 2
Forecasting system behavior and building anomaly detection flows for operational metrics.
Time Series Modeling and Forecasting
Day 2
Forecasting system behavior and building anomaly detection flows for operational metrics.
Theoretical Part
- System metrics as time series
- Forecasting versus anomaly detection
- Seasonality, trend, granularity, and noise
- Classical models such as ARIMA and Holt-Winters
- ML and deep learning models such as Prophet, LSTM, and Facebook Kats
Practical Part
- Build a forecasting pipeline for operational metrics
- Implement anomaly detection with approaches such as Isolation Forest and DBSCAN
- Deploy a forecasting API with FastAPI
- Visualize predictions and alerts in Grafana
NLP for Logs and Intelligent Incident Analysis
Day 3
Log intelligence, incident grouping, and a capstone intelligent monitoring workflow.
NLP for Logs and Intelligent Incident Analysis
Day 3
Log intelligence, incident grouping, and a capstone intelligent monitoring workflow.
Theoretical Part
- NLP concepts for DevOps
- Tokenization and embeddings including TF-IDF, Word2Vec, and BERT
- Use cases such as log classification, root cause extraction, and semantic search
- Similarity-based incident grouping
- Incident summarization and escalation support
Practical Part
- Build a basic NLP model for log classification
- Develop a component to group incidents and extract useful summaries
- Combine forecasting, anomaly detection, and NLP modules into a unified monitoring pipeline
- Evaluate the final system with real or simulated production data
TECHNOLOGIES
Technologies used in ML & AI for DevOps
These are the tools used in the public version of the course. For private cohorts, we can swap the stack and tune the flow to your team.
Need ML & AI for DevOps for your team?
Private cohorts can be run online or on-site, adapted to your tool stack, and reshaped into a half-day, multi-day, or mixed-course program for your team.
COURSE INSTRUCTORS
Karim Baklouti
Instructor - ML & Data Platforms
Sonia Boussabeh
Instructor - Data & ML Engineering
Upcoming cohorts
Date / PeriodSession 1: February 2026Online — Online via Teams
StatusOpen
Actions
Date / PeriodSession 2: May 2026Online — Online via Teams
StatusOpen
Actions
Frequently asked questions
Everything you need to know about ML & AI for DevOps.
Do participants need a strong machine learning background for ML & AI for DevOps?
A deep ML background is not required. Comfort with Python, operational data, and DevOps workflows is the main expectation, and the course introduces the relevant ML techniques in context.
Will participants build real AI workflows during the course?
Yes. The course includes hands-on work with experiment tracking, anomaly detection, forecasting pipelines, API deployment, and log analysis workflows.
Can the AI for DevOps course be tailored to a specific platform or observability stack?
Yes. Private team delivery can focus on the team's actual metrics, logs, incident workflows, and platform constraints.