Mythic
Compiler Engineer – MLIR / PyTorch Infrastructure
Palo Alto, CA +3 · Remote · Full-time · Posted Oct 3, 2025
- Location
- Palo Alto, CA
Austin, TX
Vancouver, BC
Remote - Experience
- 3+ years of experience in compiler or high-performance systems development.
About the job
Develop Mythic’s MLIR-based compiler stack, integrating PyTorch and other frameworks with hardware-aware representations for analog accelerators and digital subsystems.
What you'll do
- Migrate the existing compiler flow to MLIR by defining dialects, passes, and lowering strategies.
- Build conversion and validation paths between MLIR and Mythic’s custom low-level IR, including simulation and debugging support.
- Extend MLIR integration across hardware and guide PyTorch compiler integration.
What they ask for
- Proficiency in modern C++ (C++14/17/20) and Python.
- Hands-on experience with MLIR, including dialect design, compiler passes, or lowering pipelines.
- Strong understanding of compiler IRs and transformations, including lowering high-level operations to hardware-aware representations.
Nice to have
- Experience architecting complete MLIR flows and converting to or from existing IRs.
- Familiarity with PyTorch compiler technologies, dataflow architectures, scheduling, memory orchestration, or specialized accelerators.
Tools
MLIR, PyTorch, C++14/17/20, Python, Torch-MLIR, TorchInductor, TorchDynamo
AI focus
Build compiler infrastructure for AI hardware and integrate PyTorch and other frameworks with Mythic’s analog accelerators and digital subsystems.
Model-written summary · the original posting is authoritative