We’re a lean London-based team building a real-time AI system that does visual game state recognition + voice-based guidance with sub-second latency. The stack involves computer vision, OCR/visual embeddings, STT/TTS, WebRTC/LiveKit, and multi-agent LLM orchestration.
You’re a fit if you’ve shipped production systems in these areas — not just used the APIs. Bonus if you’re the person in the team who finds the new model/tool before everyone else does, and you actually play games. Onsite London. DM if interested or if you know someone. amira@gingerbread.solutions