AI systems inside a live product environment
Built across engineering automation, player behavior, experimentation, and cloud operations for a live mobile product. The work required reliable systems that fit existing team workflows and production constraints.
Built
LLM-assisted CI/CD automation, reinforcement-learning agents, behavioral personalization, and A/B testing infrastructure.
Evidence
A personalization engine supporting 950+ offer variants and AI agents trained on real player movement data.
Python · TypeScript · C# · PyTorch · AWS · Azure · GCP · Docker · Kubernetes