Your Responsibilities

• Design, extend and maintain our FastAPI-based backend
• Optimize low-latency, real-time communication flows (WebRTC or similar)
• Deploy and manage AI workloads on GPU infrastructure
• Improve system reliability, observability and scalability
• Contribute to DevOps processes (Docker, cloud environments, onPrem)

Your Profile

• 5+ years of backend engineering experience
• Strong Python experience (FastAPI or similar frameworks)
• Experience with asynchronous systems and performance optimization
• Solid understanding of infrastructure and containerization (Docker)
• Experience with real-time or streaming systems (WebRTC, RTP, streaming pipelines, etc.)
• Ability to work independently and take responsibility for production systems

Nice to Have

• Experience deploying ML/AI models in production
• Experience with GPU-based inference environments
• Kubernetes knowledge
• Experience with distributed systems and scaling strategies

What We Offer

• High technical ownership in a focused engineering team
• Challenging real-time AI infrastructure problems
• Flexible remote setup within European time zones
• Long-term product vision