Intern - Memory Performance and Power Modeling
Core
Analyze AI/ML workloads to characterize memory behavior, generate traces, and uncover performance bottlenecks across training and inference applications.
Role type
Intern, AI/ML Workload Analysis
Builds
Memory trace-based workload analysis, performance models, and architecture simulation environments
Domain
Semiconductor, AI/ML, Computer Architecture
Deliverable
production ML models
Required skills
Python, C/C++, Computer Architecture, Machine Learning, Parallel Computing, Operating Systems, Data Structures, Performance Analysis
Preferred skills
PyTorch, TensorFlow, JAX, ONNX, LLMs, transformers, workload profiling, simulation tools (Gem5, Accel-Sim), performance profilers (Nsight, VTune)
