Computer vision C++ Engineer

Job Description:

We are seeking a highly skilled and experienced C++ Engineer to join our team. The primary responsibility will be converting existing Python-based computer vision and deep learning (CVDL) code into optimized, production-ready C++ code. The ideal candidate should be proficient in working with C++ frameworks and libraries, including TensorFlow, PyTorch, ONNX, MNN, NCNN, TensorFlow Lite (TFLite), MMDeploy, etc. The resulting C++ code will be used across Windows and Ubuntu environments, with a strong emphasis on cross-platform compatibility and performance optimization.

• Key Responsibilities: Convert Python-based CVDL (Computer Vision and Deep Learning) pipelines into optimized C++ implementations.
• Implement models and algorithms using C++ frameworks such as TensorFlow, PyTorch, ONNX, MNN, NCNN, TensorFlow Lite (TFLite), MMDeploy, and other relevant libraries.
• Optimize code for performance, ensuring efficient use of resources, especially in real-time processing pipelines.
• Ensure cross-platform compatibility, building C++ code that works seamlessly on both Windows and Ubuntu using CMakeLists.
• Debug, profile, and optimize deep learning inference pipelines, addressing issues related to memory usage, speed, and accuracy.
• Collaborate with AI teams to understand the Python codebase, gather requirements, and ensure the successful porting of features.
• Maintain up-to-date knowledge of the latest developments in C++ frameworks, deep learning inference engines, and performance optimization techniques.

• Requirements:Experience:

- 5+ years of experience in C++ software development, specifically in converting Python code into C++.

- 3 + years of experience with computer vision and deep learning frameworks such as TensorFlow, PyTorch, ONNX, MNN, NCNN, TensorFlow Lite (TFLite), MMDeploy , Mediapipe and Bazel build system.

- Solid experience in cross-platform development for both Windows and Ubuntu using CMakeLists.

• Programming Skills:

- Proficiency in C++ (C++11/14/17) with a deep understanding of memory management, multi-threading, and performance optimization.

- Familiarity with Python, specifically in computer vision and deep learning applications, to interpret and convert code accurately.

- Strong knowledge of CMake for building cross-platform applications.

• Technical Expertise:

- Experience working with deep learning models and converting models between different formats (e.g., TensorFlow to ONNX, PyTorch to NCNN, etc.).

- Experience with OpenCV and other related computer vision libraries.

- Understanding of inference optimizations such as quantization, pruning, and model acceleration will be plus.

• Communication:

- Strong problem-solving skills and the ability to work in a collaborative, fast-paced environment.

• - Ability to communicate effectively with cross-functional teams, including data scientists, ML engineers, and Python developers.