• Developing and maintaining creative, hands-on technical samples that highlight platform capabilities through real-world AI use cases • Building and documenting distributed systems designed for global scale and high-performance inference at the edge • Creating high-quality written and video content, including deep-dive Youtube tutorials and efficient, engaging short-form videos for social platforms • Optimizing and demonstrating LLM inference on GPUs, focusing on performance, latency, and efficiency within the open-source ecosystem • Leading community building efforts by engaging with developers on GitHub, Discord, and at industry events to foster a culture of technical excellence • Contributing to the open-source LLM ecosystem and ensuring our tools integrate seamlessly with popular AI frameworks and libraries • Providing actionable feedback to internal engineering teams baed on hands-on testing and developer community insights • Representing the company through technical storytelling at conferences, workshops, and live-coding sessions • Engage with the developer community in SF and the Bay Area and globally