En ligne, en directENadvanced
AI Engineering for Senior Backend Developers
Ship production LLM features without the hype. RAG, evals, cost control, and guardrails — from a working AI platform team.
Over four live sessions you'll build a production-grade LLM feature end to end: retrieval, evaluation harnesses, cost and latency control, and safety guardrails. Every session uses real (sanitized) cases from a live fintech AI platform.
Programme · 4 sessions
1
Retrieval that actually works
Aug 18, 2026, 06:00 PM · 90 min
2
Evals & regression harnesses
Aug 20, 2026, 06:00 PM · 90 min
3
Cost, latency & caching
Aug 25, 2026, 06:00 PM · 90 min
4
Guardrails & shipping safely
Aug 27, 2026, 06:00 PM · 120 min
Votre intervenant
Staff Engineer · AI Platforms
15 years building data and ML platforms at scale. Currently leading AI infrastructure at a European fintech. Teaches from production systems, not slides.
Voir le profil complet →