Software Engineering Intern
As a Software Engineering Intern, I contributed to the deployment and optimization of Small Language Models (SLMs) on iOS devices. My work focused on ensuring efficient, private, and offline language inference to enhance user experience. I also developed context-aware prompts tailored to user behavior and document type. • Deployed SLMs fully on-device for private and offline use • Built context-aware prompt suggestions for diverse document types • Analyzed user behavior patterns to improve prompt relevance • Developed solutions to enable low-latency inference on iOS