Summer 2024 - AI Hardware Research Intern: Algorithm-Hardware Co-Design (5324)

Summer 2024 - AI Hardware Research Intern: Algorithm-Hardware Co-Design (5324) Overview of Role TSMC Corporate Research Organization is seeking a talented and motivated individual to join our team as an AI hardware research intern for Summer 2024. You will be part of our research team, focusing on a cutting-edge project related to AI hardware-algorithm co-optimization. This is a unique opportunity to gain hands-on experience for students interested in multiple facets of AI accelerator design. This position is in TSMC San Jose office and we are currently operating in a hybrid work schedule with 3 days in office. This Internship Program is open to students currently enrolled in a degree-seeking university that are preferably graduating in 1-2 years with a PhD degree. The Summer 2024 internship will begin in May 2024 and continue through at least August 2024. Responsibilities Exploration of emerging data formats with respect to AI accelerator PPA and application-level accuracy Benchmark vs. INT8 and FP16 formats Minimum Qualifications Ph.D. Student in Electrical Engineering or Computer Science Hands-on experience on: AI accelerators MAC unit implementation including Compute-In-Memory Floating-Point data formats Post-training quantization and quantization-aware training Transformers for predictive and generative applications Python and Pytorch Preferred Qualifications Quick learner Problem solver with minimal supervision Creative Self-driven and proactive Team player Excellent communicator Company Description As a trusted technology and capacity provider, TSMC is driven by the desire to be: The world’s leading dedicated semiconductor foundry The technology leader with a strong reputation for manufacturing excellence Advancing semiconductor manufacturing innovations to enable the future of technology TSMC pioneered the pure-play foundry business model when it was founded in 1987 and has been the world’s leading dedicated semiconductor foundry ever since. The Company supports a thriving ecosystem of global customers and partners with the industry’s leading process technologies and a portfolio of design enablement solutions to unleash innovation for the global semiconductor industry. With global operations spanning Asia, Europe, and North America, TSMC serves as a committed corporate citizen around the world. In North America, TSMC has a strong sales and service organization that works with customers by helping them achieve silicon success with cutting-edge technologies and manufacturing excellence. The Company has continued to accelerate its R&D investment and staffing in recent years and is expanding its manufacturing footprint to support customer innovation with 3D IC technologies and optimal manufacturing capacity. For positions requiring access to technical data subject to export control regulations, including Export Administration Regulations, TSMC North America may have to obtain export licensing approval from the U.S. Government for certain individuals. All employment is contingent upon TSMC North America obtaining any export license or other approval that may be required by the U.S. Government. Diversity statement TSMC Technology, Inc. is committed to employing a diverse workforce and provides Equal Employment Opportunity for all individuals regardless of race, color, religion, gender, age, national origin, marital status, sexual orientation, gender identity, status as a protected veteran, genetic information, or any other characteristic protected by applicable law. TSMC is an equal opportunity employer prizing diversity and inclusion. We are committed to treating all employees and applicants for employment with respect and dignity. If you require reasonable accommodation due to a disability during the application or the recruiting process, please feel free to notify us at View email address on click.appcast.io. TSMC confirms to all applicants its commitment to meet TSMC’s obligations under applicable employment law. Reasonable accommodations will be determined on a case-by-case basis. #J-18808-Ljbffr