🛠 Tech Stack

💼 About This Role

You'll own the bridge between research breakthroughs and production systems, turning research checkpoints into production-ready inference services. You'll design and maintain high-performance APIs serving millions of requests and optimize inference latency across GPU infrastructure. This role removes the bottleneck between frontier research and production reality.

🎯 What You'll Do

• Turn research checkpoints into production-ready inference services
• Design and maintain high-performance APIs serving millions of requests
• Optimize inference latency and throughput across GPU infrastructure
• Build scalable serving architectures that handle unpredictable traffic

📋 Requirements

• Experience building and operating ML inference services in production
• Proficiency in Python, FastAPI, and async systems
• Experience scaling APIs or ML systems under load
• Comfort working in fast-moving, research-adjacent environments

✨ Nice to Have

• Real-time or low-latency inference systems
• TensorRT, reduced precision, or model compilation
• Frontend demo tooling (Streamlit, Gradio, React)

🎁 Benefits & Perks

• 🏖️ Flexible Hybrid Work
• 🌍 International Team with offices in Freiburg and SF
• 🚀 Cutting-Edge AI Research environment
• 💻 Open Science Culture

📨 Hiring Process

Estimated timeline: 2-4 weeks · AI estimate

1. 1Recruiter Call· 30 min
2. 2Technical Interview· 60 min
3. 3System Design Interview· 60 min