Cajetan Rodrigues
Software @ Volvo Cars
Göteborg, Sweden
Actions
Cajetan is a full-spectrum engineering leader seasoned in solving complex business challenges, with nearly 15 years of experience in a mix of domains like Banking & Finance, Travel & Hospitality, Transportation & Logistics, Automotive, etc. He loves building great products, teams, and awesome engineering cultures. Currently an Open Source Champion at Volvo Cars, in his free time he enjoys visiting libraries, experimenting with new cuisines, long walks and hikes, and playing board games.
Area of Expertise
Topics
Zero-cloud setups for LLM/GenAI observability
As GenAI shifts from cloud APIs to localized, fine-tuned models running directly on developer workstations, traditional logging has already fallen short. Large Language Models (LLMs) introduce complex failure modes: non-deterministic outputs, opaque agentic loops, hidden prompt injection risks, and unpredictable token-based latency. To build reliable applications, engineers need deep observability long before their code hits a production cluster. Crucially, they need it without sending sensitive proprietary prompts to external cloud vendors.
This session provides a highly practical, architectural guide to implementing end-to-end LLM observability entirely on your local development machine. We will explore the modern open-source landscape, detailing how to capture spans, trace multi-turn conversations, evaluate retrieval-augmented generation (RAG) quality, and track system resources locally. Walk away with a clear blueprint for comparing and deploying: in-process diagnostic engines like Arize Phoenix for instant, notebook-based tracing, self-hosted Docker stacks such as Langfuse for comprehensive agent and prompt management, standardized semantic conventions via OpenTelemetry, OpenLLMetry, and OpenLIT to cleanly decouple application logic from telemetry backends. Whether you are building basic wrapper scripts or complex autonomous agent networks via Ollama or vLLM, this talk equips you with the tools to debug, profile, and optimize your local AI stack securely and efficiently.
“Security at the Speed of BPF: Building a Lightweight SIEM with eBPF + OpenSearch”
Security observability is undergoing a quiet revolution—and at its heart is eBPF, the powerful in-kernel technology enabling deep, zero-overhead visibility into system behavior. In this talk, we’ll explore how eBPF can be combined with OpenSearch to build a high-performance, real-time SIEM (Security Information and Event Management) pipeline—without the heavyweight infrastructure of traditional security stacks.
You’ll learn how to use eBPF to trace critical security signals like syscall events, file access patterns, unauthorized network connections, and privilege escalations—all from kernel space, with minimal performance impact. Then we’ll walk through how to structure, enrich, and ship these events directly into OpenSearch, where they can be indexed, queried, and visualized for active threat detection and forensic analysis.
We’ll close with a live demo of a “lightweight SIEM in action”—catching threats on a Linux system using eBPF sensors and surfacing alerts in OpenSearch in real time.
Whether you're a security engineer, SRE, or search architect, this session will show how eBPF and OpenSearch can form a fast, open, and flexible foundation for next-generation SecOps.
Cajetan Rodrigues
Software @ Volvo Cars
Göteborg, Sweden
Actions
Please note that Sessionize is not responsible for the accuracy or validity of the data provided by speakers. If you suspect this profile to be fake or spam, please let us know.
Jump to top