Deep Learning Compiler Intern - 2027
Core
Design and implement the DSL and core compiler for a tile-aware GPU programming model to optimize performance for emerging GPU architectures and AI/LLM workloads.
Role type
Deep Learning Compiler Architect (Intern)
Builds
Next-generation GPU architectures, compiler stacks, and DSLs for parallel processing algorithms.
Domain
Hardware/Software co-design, GPU architecture, High-Performance Computing (HPC), AI/ML frameworks.
Deliverable
production ML models
Required skills
C/C++ programming, computer architecture fundamentals, compiler development (MLIR/TVM/Triton/LLVM), abstract problem solving, kernel programming.
Preferred skills
LLM algorithms, multi-GPU distributed communication, agentic coding workflows, ACM background.
Technologies
MLIR, TVM, Triton, LLVM, CUDA, AI/ML frameworks.
Responsibilities
Design and implement DSLs and core compilers for tile-aware GPU models; iterate on compiler architecture to optimize performance; investigate next-gen GPU architectures; analyze performance on AI/LLM workloads.
Seniority
Intern
