AI Compiler Design Engineer

AI Compiler Design Engineer

Location:

Austin, Texas (This position is not remote).

Traditional compiler designers focus on breaking down high level software programs into low-level machine language and/or assembly. We are looking for engineers who want to create compilers for specialized AI workloads. Most AI compiler engineers optimize models for GPUs that already exist. You will optimize them for silicon that does not yet.

• Define the framework and data flow for building an optimized compiler at the lowest level.
• Own the stack: design and implement custom MLIR dialects from scratch, including Table Gen definitions, transformation passes, and dialect conversion infrastructure.
• Lower and legalize high‑level computational graphs exported from JAX and StableHLO into hardware‑specific IR while preserving full mathematical fidelity.
• Build static scheduling and tiling passes to orchestrate data movement between HBM and on‑chip local memory, ensuring precise memory usage.
• Maintain a high‑performance, modular, LLVM‑based compiler codebase in C++, ensuring correctness and determinism.

Ericsson is an equal opportunity employer. If you need assistance or a disability accommodation, please contact hr

DISCLAIMER:
The above statements are intended to describe the general nature and level of work being performed by employees in this position. They are not an exhaustive list of all responsibilities, duties, and skills required for this position, and you may be required to perform additional job tasks as assigned.