AI Compiler Engineer - Remote (US & Canada)

Job Description

Job Description

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.
What You'll Do

• 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.

• 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.