About
Caspar is the Head of Product at Lyceum, where he drives product strategy and ensures the platform meets the needs of AI teams across Europe.
Before joining Lyceum, Caspar gained extensive experience in product development and technology, with a focus on building user-centric solutions for complex technical challenges.
At Lyceum, Caspar oversees the end-to-end product experience — from GPU provisioning workflows to developer documentation — ensuring that AI infrastructure remains accessible to teams of all sizes.
Published Articles
Sovereign AI Infrastructure
LLM Inference & Model Serving
- • Serverless GPU Cold Start Latency: Architecture Comparison
- • Llama 3 vs Mistral vs Qwen: 2026 Inference Benchmark Guide
- • RAG Pipeline GPU Infrastructure: The Engineering Guide
- • The Guide to Serving Fine-Tuned LLMs in Production
- • Deploy a Hugging Face Model Inference API: 2026 Production Guide
- • Self-Host LLM APIs on EU Infrastructure: The Modern Guide
- • OpenAI Compatible API Self Hosted: A Guide for EU AI Teams
- • Host Fine-Tuned Model Production APIs: A Technical Guide
- • Deploying Custom Docker Model Inference APIs for Production
GPU Cost Optimization
- • Open Source vs Closed API LLM Cost Comparison
- • Inference Cost Per Token vs. Dedicated GPU: 2026 Economics
- • Which GPU for Fine-Tuning 70B Models? A Technical Guide
- • H100 80GB vs A100 80GB: Fine-Tuning Performance and TCC Analysis
- • GPU Memory Requirements for Transformer Models: A Technical Guide
- • GPU for 7B vs 70B Model: A Technical Infrastructure Guide
- • Solving the 40 Percent GPU Cluster Utilization Problem
- • Dedicated GPU vs Cloud Instance: The Engineer's Guide to AI Infrastructure
- • Best GPU for Llama 3 Fine-Tuning: A Technical Engineering Guide
- • Hardware Recommendations for LLM Fine-Tuning: The 2026 Guide
- • How to Right Size GPU Instances for ML Workloads
- • Optimize Slurm GPU Allocation for High Performance AI Workloads
- • How Many GPUs for Model Training? A Practical Scaling Guide
- • H100 vs A100 Cost Efficiency: A Technical Deep Dive
- • GPU Selection Guide for ML Training: 2026 Performance Benchmarks
- • A100 vs H100 for LLM Inference: The Engineer’s Guide to Efficiency
Production GPU Infrastructure
GPU Memory Management
GPU Infrastructure & Cost Engineering
GPU Cloud Migration & Alternatives
EU-Sovereign AI Compute
Want to join the team?
We're always looking for exceptional engineers and builders who care about infrastructure.