Machine Learning Intern (Singapore)

**About the Role** We are seeking a Software Intern to support the development of tools, frameworks, and applications that enable neural network models to run efficiently on TetraMem’s novel analog compute\-in\-memory chips. This is an exciting opportunity to work at the intersection of software, hardware, and artificial intelligence. **Responsibilities** * **Responsibilities** * Develop, optimize, and maintain Python and C\+\+ software for neural network model compression, conversion, deployment, and runtime environments. * Design and implement tools to improve machine learning model efficiency, including quantization, pruning, graph optimization, and memory reduction techniques. * Analyze and adapt machine learning models to improve compatibility, performance, and power efficiency on Compute\-in\-Memory (CIM) and Analog AI hardware architectures. * Develop software frameworks, APIs, and runtime components to support end\-to\-end AI model deployment on edge AI and embedded systems. * Perform software design, implementation, debugging, testing, and performance profiling to optimize system throughput, latency, and resource utilization. * Collaborate closely with AI researchers, hardware engineers, and system architects to validate hardware\-software co\-design and system\-level functionality. * Evaluate emerging machine learning models, algorithms, and deployment techniques to enhance AI inference performance on next\-generation semiconductor platforms. * Participate in code reviews, establish software quality standards, and contribute to automated testing, continuous integration, and technical documentation. * Troubleshoot software and system issues across the AI stack, including model conversion pipelines, runtime environments, and hardware acceleration frameworks. * Contribute to the development of innovative AI computing technologies and support research activities through technical presentations, publications, patents, and cross\-functional collabo