Principal AI Compiler Engineer

Role: Principal AI Compiler Engineer (Staff/Principal)
Type: Hybrid / Remote
Locations: Bangalore, India | Remote Opportunities Available

About the Role: EnCharge AI seeks an experienced Principal AI Compiler Engineer to lead efforts in developing and optimizing graph compilers for cutting-edge AI workloads. Collaborate with hardware architects and researchers to enhance performance on Inference Accelerators.

Key Responsibilities

• Architect, design, and implement optimizations for AI model execution (layer fusion, operator fusion, graph-level transformations).
• Develop compiler passes converting high-level models (TensorFlow, PyTorch) into intermediate representations.
• Implement parsing, semantic analysis, and IR generation for deep learning frameworks.
• Led research on hardware acceleration integration; provide technical guidance to engineering teams.

Qualifications

• Bachelor's or Master's in CS/EE (Ph.D. preferred).
• 10-15 years experience in compiler development with a focus on AI graph compilers.
• Mastery of MLIR, Torch-FX; strong background in GPU/TPU optimization (quantization, tiling).
• Proficiency in C++, Python; open-source contributions to AI frameworks are highly valued.