AI Compiler Engineer

AI Compiler Engineer

About the Role

We are seeking a highly skilled and experienced AI Compiler Engineer to lead efforts in developing and optimizing graph compilers tailored for cutting-edge AI and ML workloads. You will collaborate with hardware architects, researchers, and software developers to enhance performance, optimize computation graphs, and enable efficient model deployment on EnCharge's Inference Accelerators.

Responsibilities

• Architect, design, and implement optimizations for AI model execution on graph compilers to improve performance, reduce latency, and maximize hardware utilization.
• Collaborate with ML researchers, hardware engineers, and software developers to deploy AI models while addressing hardware-specific challenges.
• Perform performance optimizations for neural network models, including layer fusion, operator fusion, and graph-level transformations.
• Develop compiler optimizations and passes that convert high-level AI models (e.g., from TensorFlow, PyTorch) into intermediate representations (IR).
• Implement parsing, semantic analysis, and IR generation for deep learning frameworks.
• Research and integrate the latest advancements in compiler design, ML model optimizations, and hardware acceleration.
• Provide leadership, mentorship, and technical guidance to a team of engineers focused on graph compiler optimizations.

Qualifications

• Master's degree in Computer Science, Electrical Engineering, or related field (Ph.D. preferred).
• 2-4 years in compiler development with a strong focus on AI/ML graph compilers.
• Proficiency in frameworks like MLIR and Torch-FX.
• Solid background in hardware architectures (GPUs, TPUs, ASICs) and optimization techniques such as fusion, quantization, and tiling.
• Familiarity with neural network operators and code generation.
• Strong understanding of IRs, code parsing, and semantic analysis.
• Proficiency in C++, Python, or other relevant programming languages.