Job Title: Research Engineer (AI Accelerator and Energy-Efficient Computing)
University-Level Unit: College of Design and Engineering
Faculty/Department-Level Unit: Electrical and Computer Engineering
Employee Category: Research Staff
Location_ONB: Kent Ridge Campus
Posting Start Date: 13/04/2026
Job Description
We are seeking a highly motivated and skilled Research Engineer to join our team in developing next-generation energy-efficient AI hardware. The project aims to demonstrate an AI accelerator chiplet that integrates emerging non-volatile memory (RRAM or MRAM) with conventional I/O interfaces. This platform will showcase compute–memory co-design advantages, including enhanced data throughput, improved energy efficiency, and reduced data-movement overheads for large-scale AI workloads.
Key Responsibilities
- Develop and implement fine-grained dynamic voltage and frequency scaling (DVFS) strategies tailored for GPU-based AI workloads, with control at the level of transformer blocks and attention layers.
- Design and build a high-resolution (microsecond-scale) performance monitoring framework to capture workload intensity, memory access patterns, and GPU utilization for real-time optimization.
- Develop and deploy machine learning models to predict optimal voltage–frequency operating points during LLM training and inference.
- Integrate predictive control algorithms with hardware platforms to enable real-time, adaptive power management across heterogeneous compute and memory subsystems.
- Collaborate on system-level hardware–software co-design to realize energy-efficient AI acceleration.
- Contribute to prototype development, benchmarking, and evaluation of performance and energy efficiency.
- Publish research findings in leading journals and present at international conferences.
- Mentor undergraduate students and support team-based research activities.
Qualifications
- Bachelor’s or Master’s degree in Computer Engineering, Computer Science, or a related field.
- Strong programming skills in Python and C/C++, with experience in machine learning frameworks such as PyTorch or TensorFlow.
- Familiarity with deep learning models—particularly transformer architectures and large language models (LLMs)—is advantageous.
- Experience or interest in system-level optimization (e.g., DVFS, workload profiling, or power management) is a plus.
- Strong analytical and problem-solving skills, with the ability to conduct independent research and contribute to technical publications.
- Ability to work effectively in a multidisciplinary environment, with good communication skills, initiative, and adaptability.