How do you turn a two-week, multi-account infrastructure runbook into a one-hour conversation? This session presented a re-imagined developer portal experience built on Strands Agents SOPs: architecture decisions, security constraints, and deployment steps codified once as machine-readable runbooks (RFC 2119 keywords, parameterized inputs, progress tracking), executed by an agent that generates Terraform and application code, monitors deployments, and adapts to failures — with a human setting parameters, reviewing the plan, and gating production. The live demonstration took a web application from description to production across three AWS accounts: ~150 resources, 6 Terraform modules (VPC, ALB, CloudFront, ECS, RDS, Cognito), in under an hour. Presented at the AWS AI SDLC Workshop in Vienna.
Conference, Cloud Conference, University of Applied Sciences Burgenland, Burgenland, Austria
Presented a 30-minute session on Generative AI lifecycle tooling to an audience of approximately 200 attendees at a cloud computing conference. Covered the end-to-end lifecycle of foundation models, from experimentation and evaluation to deployment and monitoring, using AWS services. The session led to a follow-up conference with business decision makers.
Co-presented with Ankit Anand and Matt Nightingale, this session explored the challenges of training foundation models at scale and how Amazon SageMaker HyperPod addresses them. The talk covered the generative AI landscape and the growing computational demands of FM development, from prompt engineering and RAG to full pre-training. We introduced SageMaker HyperPod as a resilient, performant, and customizable environment for large-scale distributed training — featuring self-healing clusters that automatically detect hardware failures, replace faulty instances, and resume training jobs from checkpoints, reducing training time by up to 20%. The session went under the hood of HyperPod, covering cluster architecture, instance groups, lifecycle scripts, Elastic Fabric Adapter (EFA) for high-speed inter-node communication, distributed training software stacks for both GPU and Trainium, and job scheduling with auto-healing. Customer stories from Stability AI, Perplexity AI, and Hugging Face illustrated real-world benefits.
Presented LLMOps and FMOps concepts to approximately 100 attendees at an AWS builder-focused event, covering the operational lifecycle of large language models including fine-tuning, evaluation, deployment, and monitoring strategies.
Conference, AWS Cloud Day Zurich, Zurich, Switzerland
This talk presented a comprehensive overview of MLOps on AWS, covering the journey from experimental notebooks to production-ready ML systems using Amazon SageMaker. Starting from the premise that ML code is only a small fraction of a real-world ML system, the session walked through an MLOps maturity framework across four phases — Initial, Repeatable, Reliable, and Scalable — mapping each to specific AWS services and capabilities. Topics included SageMaker Studio for experimentation, SageMaker Experiments for tracking, SageMaker Pipelines for workflow automation, Model Registry for versioning and promotion, SageMaker Projects for one-click CI/CD provisioning, shadow testing and deployment guardrails, Model Monitor for drift detection, and Model Cards and Dashboard for governance. The talk also covered team structures, multi-account strategies, and custom project templates for enterprise-scale MLOps.
Meetup, Vienna Data Science Tools Meetup, Vienna, Austria
Presented on foundation model hosting options and demonstrated a Retrieval-Augmented Generation (RAG) application at the Vienna Data Science Tools Meetup, with approximately 60 attendees from the local data science community.
Delivered two hands-on AWS DeepRacer workshop sessions (theory and practice) at AWS Summit Milan, covering reinforcement learning fundamentals and autonomous racing. Both sessions were at full capacity with 30+ attendees each. Delivered in Italian.
Delivered an MLOps session as part of the Italian-language track at AWS Innovate, covering end-to-end machine learning workflows on Amazon SageMaker. Also participated in an Ask The Expert panel and live Q&A session. Approximately 200 attendees.
Recorded a 40-minute podcast episode on MLOps with Alex Casalboni for the official AWS Italy Podcast, discussing automation strategies for machine learning workflows, SageMaker Pipelines, experiment tracking, and best practices for production ML systems.
Organized and hosted the first AWS Vienna Meetup at the AWS Vienna office, presenting on MLflow integration with Amazon SageMaker and open-source ML tooling on AWS. The event reached full capacity with 35 attendees.
Teaching
TU Wien — External Lecturer · 2023 – Present I teach the AI and Generative AI module of the Project Course on Cloud Computing (192.035): foundation models, prompt engineering, retrieval-augmented generation, and what it takes to build AI applications on the cloud. Several cohorts of graduates so far, and the material gets rewritten every year because the field refuses to sit still.
Trinity College Dublin — Teaching Assistant · 2012 – 2015 Java programming labs for Computer Science students, and the Electrotechnics lab for engineers: oscilloscopes, measurement techniques, and low-pass filters built by hand.
