- Work from
- Canada, United States
- Contract
- Full-time
- Salary
- $190K – $255K / year
- Posted
- 16 November 2026
- Apply by
- 15 January 2027
BEARCloud's client is seeking an AI Compiler Engineer developing next-generation AI inference accelerator technology. This role will focus on building and optimizing graph compiler technology for AI/ML workloads, improving model performance, latency, and hardware utilization.
Responsibilities
- Develop and optimize AI/ML graph compilers for inference accelerators.
- Implement graph-level optimizations including layer/operator fusion, quantization, tiling, and graph transformations.
- Build compiler passes that convert PyTorch/TensorFlow models into intermediate representations (IR).
- Work with MLIR, Torch-FX, parsing, semantic analysis, IR generation, and code generation.
- Partner with AI researchers and hardware architects to optimize models for GPU, TPU, ASIC, or custom accelerator architectures.
- Analyze performance and identify opportunities to improve latency, throughput, and hardware utilization.
- Provide technical guidance and mentorship to other engineers.
Requirements
- 3+ years of compiler development experience, ideally with AI/ML graph compilers.
- Hands-on experience with MLIR, Torch-FX, LLVM, or similar compiler frameworks.
- Strong understanding of intermediate representations (IR), compiler passes, graph transformations, and code generation.
- Experience with fusion, quantization, tiling, and neural network operators.
- Knowledge of GPU, TPU, ASIC, NPU, or AI accelerator architectures.
- Strong C++ and/or Python development skills.
- BS/MS in Computer Science, Electrical Engineering, or related field; PhD a plus.
- Open-source AI/compiler contributions and technical leadership experience are a plus.
B
T
B
M
P
C
T
Discussion
No comments yet. Ask a question or share a tip about this role.