🔭 I’m currently working on: Exploring the boundaries of on-device LLMs, experimenting with mobile apps powered by local LLMs, and coupling local AI models (from image, translation to audio pipelines).
👯 I’m looking to collaborate on: Innovative open-source AI projects, multimodal applications, and bringing powerful local ML capabilities to mobile environments.
🤝 I’m looking for help with: Optimizing local LLMs for mobile devices and scaling distributed AI inference across local hardware networks.
🌱 I’m currently learning: Advanced orchestration for diverse local AI setups and expanding my full-stack capabilities for seamless multimodal integration.
💬 Ask me about: Running complex local AI inference (text, image, audio and beyond) on Apple Silicon, mobile LLM experiments, and troubleshooting tricky Python dependency trees.
⚡ Fun fact: I can orchestrate a full multimodal AI pipeline entirely on local hardware—and occasionally use it to engineer custom, high-energy Indian hip-hop tracks.
