Applied ML Engineer, Real‑Time Video Generation

📋 Description

• Productionize video generation models into robust inference APIs.
• Optimize models for latency and cost via distillation.
• Build real-time inference systems with low latency streaming and observability.
• Prototype fast: ship WebRTC demos and production features.
• Multi-GPU work: run and optimize large model components across GPUs.
• Collaborate with research to deploy models and improve performance.

🎯 Requirements

• 2+ years in ML engineering with shipped systems ownership.
• PyTorch + Python for training and inference.
• Generative models (diffusion/transformers/VAEs) for image/video.
• Improve latency and cost via profiling and memory optimization.
• Production mindset: debugging under load, monitoring, deployment hygiene.
• WebRTC/real-time media delivery; Docker and Kubernetes basics.

🎁 Benefits

• €190,000-€225,000 base salary + bonus.
• Remote in Europe (GMT +/- 2 hours).