Job Overview
We are seeking a highly skilled AI Engineer to contribute to the development of next-generation AI models and building blocks for deployment on constrained hardware devices.
This role focuses on optimizing AI models, including transformers, for edge hardware, employing techniques such as quantization, pruning, and benchmarking to create efficient and effective AI solutions.
Key Responsibilities
* Develop and Optimize AI Models: Focus on creating and refining AI models that can be efficiently deployed on edge hardware.
* Implement Optimization Techniques: Utilize techniques like quantization, pruning, and hardware-specific optimizations to improve performance.
* Collaborate with Teams: Work closely with hardware and software teams to ensure seamless integration of AI solutions into our platforms.
* Benchmark Performance: Contribute to efforts evaluating model performance and resource usage.
Qualifications
To succeed in this role, you should have a strong foundation in AI/ML model development, optimization, and deployment. We're looking for candidates with hands-on experience working with transformer models and their deployment on embedded or constrained platforms.
A Master's degree or equivalent experience in Computer Science, Electrical Engineering, or a related field is required, along with 5+ years of industry experience in AI/ML model development, optimization, and deployment.
Familiarity with Python and C++ for AI model development and integration is essential, as well as experience with AI frameworks like TensorFlow, PyTorch, or ONNX, and their optimization for hardware targets.
Preferred Skills
* Custom AI Architectures: Experience designing custom AI architectures for edge devices is highly valued.
* Problem-Solving Skills: Strong problem-solving and debugging skills for AI applications on resource-constrained devices are necessary.
* Team Collaboration: The ability to work collaboratively in multidisciplinary teams is crucial.