Staff Deep Learning Compiler Engineer

What you'll do

• Build compiler passes and model-lowering pathways, and optimize generated code for performance, latency, memory use, and power.
• Implement graph transformations and support new model architectures, operators, and primitives; benchmark and profile end-to-end performance.
• Work with hardware teams on co-design, validation, simulators, and bring-up on FPGA and ASIC platforms.

What they ask for

• BS, MS, or Ph.D. in Computer Science, Computer Engineering, Electrical Engineering, or a related field.
• 8+ years of hands-on experience developing deep learning compilers or compiler infrastructures.
• Strong proficiency in C++ (14/17/20) and Python, with solid data structures, algorithms, and object-oriented design fundamentals.
• Familiarity with PyTorch, TensorFlow, or ONNX; understanding of deep learning operator representations and computer systems, memory hierarchies, parallel processing, and CPU/GPU/NPU instruction execution.

Nice to have

• Experience with low-level kernel optimization, SIMD/vector programming, or memory allocation strategy development.
• Knowledge of quantization and post-training/QAT optimization, or experience with custom AI accelerators, DSPs, embedded architectures, FPGA bring-up, hardware emulation, or cycle-accurate simulators.

Pay

$170,000 to $230,000 USD base salary

Tools

MLIR, Apache TVM, LLVM, PyTorch, TensorFlow, ONNX, C++, Python

AI focus

Develop compiler support and optimizations for neural-network inference on edge hardware, including model parsing, graph transformations, quantization, and performance tuning.