Research And Pathfinding Internship: Ai Workload Compiler Optimization For Cpu And Gpu
Intel
Gdansk, Poland
Hybrid
Ai kernel compilation
Cpu and gpu architectures
Mlir/llvm framework
This internship focuses on developing novel optimization techniques for AI kernel compilation targeting both CPU (Intel AMX/AVX-512) and GPU architectures from a unified representation interfacing with MLIR/LLVM framework
Job Summary
This internship focuses on developing novel optimization techniques for AI kernel compilation targeting both CPU (Intel AMX/AVX-512) and GPU architectures from a unified representation interfacing with MLIR/LLVM framework.
You will explore the design and implementation of a PEG (Graph + PEG) abstraction that combines algebraic optimization and hierarchical scheduling.
Work at the intersection of research and product in a pathfinding team and contribute to Intel's compiler infrastructure for heterogeneous AI systems.
Matching Summary
This internship focuses on developing novel optimization techniques for AI kernel compilation targeting both CPU (Intel AMX/AVX-512) and GPU architectures from a unified representation interfacing with MLIR/LLVM framework.
Skills & Requirements
Must-have
AI kernel compilation
CPU and GPU architectures
MLIR/LLVM framework
algebraic optimization
hierarchical scheduling
Nice-to-have
probabilistic and symbolic methods
Intel AMX/AVX-512 features
publication opportunities
Key Requirements
Experience with compiler internals
Programming skills: Python and C++
Familiarity with CPU architectures
Current student in Computer Science or related field