About
Justus leads Go-to-Market initiatives at Lyceum, helping AI teams discover and adopt GPU infrastructure that accelerates their work.
With a background in technology and business development, Justus focuses on understanding customer needs and translating them into product and market strategies.
At Lyceum, Justus works closely with AI teams across Europe to ensure they can access the compute resources they need, when they need them — without the complexity traditionally associated with GPU infrastructure.
Published Articles
Serverless Inference Model Library
- • Qwen3.5-397B-A17B: specs, benchmarks, and how to run it on Lyceum
- • Qwen2.5-VL-72B: specs, benchmarks, and how to run it on Lyceum
- • Nemotron-3-Nano-Omni: specs, benchmarks, and how to run it on Lyceum
- • Llama-3.3-70B: specs, benchmarks, and how to run it on Lyceum
- • Hermes-4-405B: specs, benchmarks, and how to run it on Lyceum
- • FLUX.2 Klein: specs, benchmarks, and how to run it on Lyceum
Sovereign AI Infrastructure
LLM Inference & Model Serving
- • vLLM vs TensorRT-LLM: Production Benchmark & Guide
- • Streaming Inference API: Architecting Real-Time AI Agents
- • Run Vision Language Models on GPU Cloud: VRAM & Setup Guide
- • Deploying Microsoft Phi-4 Inference on GPU Cloud: A Production Guide
- • Serverless GPU Inference: Architecture, Economics, and Compliance
- • Pay Per Token vs Dedicated GPU Inference: The Break-Even Guide
- • Self-Hosted LLM API Gateway Guide: Architecture and Infrastructure
- • Deploying Llama 3 Inference APIs on Sovereign GPU Clouds
Production GPU Infrastructure
GPU Memory Management
GPU Cost Optimization
- • On-Premise vs Cloud GPU Breakeven: The 2026 Infrastructure Guide
- • Spot Instance GPU ML Training: A Technical Guide for AI Teams
- • Nvidia H100 Availability Europe: A Guide for AI Engineering Teams
- • Lambda Labs vs RunPod vs Vast.ai: Choosing Your GPU Cloud
- • The Engineer's Guide to GPU Clouds with No Egress Fees
- • Egress Fees GPU Cloud Comparison: The Hidden Cost of AI
- • CoreWeave vs Lambda GPU Cloud: The ML Engineer’s Guide to GPU Clusters
- • Colocation vs Cloud GPU for ML: An Engineering Guide
- • AWS P5 H100 Pricing Per Hour 2026: A Technical Cost Analysis
- • Navigating the AWS GPU Price Increase in 2026
- • GPU ROI: Beyond the Hourly Rate in ML Infrastructure
- • Stopping the Bleed: The $15B Crisis of GPU Overprovisioning
- • The Cost Per Training Run Calculator: A Guide for ML Engineers
- • Strategies to Reduce GPU Cloud Costs for ML Training
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.