C++ Quantization Engineer - Edge AI
- Source: Naukri
- Kinara Ai
- On-site
- Hyderabad
- Full-Time
- Mid level
Job Description
Job Summary
We are looking for a C++ Quantization Engineer specializing in Edge AI to optimize machine learning models for deployment on resource-constrained devices. The role involves implementing quantization techniques, enhancing inference performance, and collaborating with AI and embedded system teams.
Key Responsibilities
- Develop and optimize C++ solutions for AI model deployment.
- Implement model quantization techniques (INT8, FP16, mixed precision).
- Improve inference speed, memory utilization, and power efficiency.
- Work with TensorFlow Lite, ONNX Runtime, TensorRT, or similar frameworks.
- Profile and debug Edge AI applications.
- Collaborate with data scientists, AI researchers, and firmware teams.
- Validate model accuracy after quantization and optimization.
- Develop deployment pipelines for embedded and edge devices.
Required Skills
- Strong programming skills in C++.
- Experience in AI/ML model optimization and quantization.
- Knowledge of deep learning frameworks and deployment tools.
- Understanding of embedded systems and hardware acceleration.
- Experience with ARM, DSP, NPU, GPU, or edge computing platforms.
Skills
- cplusplus
- Tensorflow
- tensorflow-lite
