Chief Engineer Deep Learning Compiler Expert

Mindstech Recruitments; India; On-site; INR 1,200,000 - 2,000,000; Full time

Job summary

Mindstech Recruitments is hiring a Chief Engineer specializing in Deep Learning Compiler to work on deploying machine learning models onto Samsung Mobile AI platform. The role involves design and implementation of compiler features, collaboration with ML experts, and optimizing compiler capabilities for high-performance.

The ideal candidate should have extensive experience in compiler design, knowledge of open-source technology like MLIR and LLVM, and strong programming skills in modern C++. A M.S. or higher in a relevant field is required.

Qualifications

• 6 to 15 years of experience in compiler design and graph mapping.
• 2+ years of hands-on experience with MLIR and/or LLVM.
• Strong knowledge of resource management, scheduling, code generation, and compute graph optimization.

Responsibilities

• Design, implement, and test compiler features and capabilities.
• Integrate open-source and vendor compiler technology into internal infrastructure.
• Collaborate with engineers to provide guidance on inferencing direction.

Skills

Compiler design

Graph mapping

MLIR

LLVM

C++ production quality code

Machine learning frameworks

Deep learning algorithms

Education

M.S. or higher in CS/CE/EE or equivalent

Job description

As a Chief Engineer specializing in Deep Learning Compiler, your primary responsibility will be to collaborate with experts in machine learning, algorithms, and software to deploy machine learning models onto Samsung Mobile AI platform. You will contribute to the development and enhancement of the compiler infrastructure for high-performance using open-source technology like MLIR, LLVM, TVM, and IREE.

Responsibilities

• Design, implement, and test compiler features and capabilities related to infrastructure and compiler passes.
• Ingest CNN graphs in Pytorch, TF, TFLite, and ONNX format and map them to hardware implementations, model data‑flows, create resource utilization cost‑benefit analysis, and estimate silicon performance.
• Develop graph compiler optimizations customized to different ML accelerators in the system, such as operator fusion and layout optimization.
• Integrate open‑source and vendor compiler technology into Samsung ML internal compiler infrastructure.
• Collaborate with Samsung ML acceleration platform engineers to provide guidance on inferencing direction, requirements, and feature requests for hardware vendors.
• Stay updated with industry and academic developments in the ML compiler domain and provide performance guidelines and standard methodologies for other ML engineers.
• Create and optimize compiler backend to efficiently leverage the full hardware potential using novel approaches.
• Evaluate code performance, diagnose, debug, and resolve compiler and cross‑disciplinary system issues.
• Contribute to the development of machine‑learning libraries, intermediate representations, export formats, and analysis tools.
• Communicate and collaborate effectively with cross‑functional hardware and software engineering teams.
• Champion engineering and operational excellence by establishing metrics and processes for regular assessment and improvement.

Qualifications

• 6 to 15 years of experience in compiler design and graph mapping.
• 2+ years of hands‑on experience with MLIR and/or LLVM.
• Experience with multiple toolchains, compilers, and instruction set architectures.
• Strong knowledge of resource management, scheduling, code generation, and compute graph optimization.
• Proficiency in writing modern standards (C++17 or newer) C++ production quality code following test‑driven development principles.
• Familiarity with parallelization techniques for ML acceleration.
• Experience contributing to an active compiler toolchain codebase like LLVM, MLIR, or Glow.
• Deep learning algorithms and techniques expertise, e.g., convolutional neural networks, recurrent networks, etc.
• Experience with mainstream machine‑learning frameworks like PyTorch, TensorFlow, or Caffe.
• Experience in hardware and software co‑design.
• M.S. or higher degree in CS/CE/EE or equivalent with industry or open‑source experience.