Job Location: Poona
FRESHERS PLEASE DO NOT APPLY HERE.
About The Position
Were looking for a hands-on, fast learning, and tech-savvy Deep Learning Engineer with strong and demonstrated expertise in IoT systems and deep learning/AI at the edge or in a power/memory constrained environment. EDGENeural.ai has the vision to bring high-performing AI model closer to the source of the data generated. In this role, you will be working on compiling the next generation of intelligent edge AI deep learning models to be put on different set EDGE hardware and working on building inference engines to infer those models on specified EDGE hardware.
Your Responsibilities
- Design and implement EDGE AI models using deep learning NNs base models, techniques, and platforms for certain computer vision and Natural Language Processing applications.
- Engage in all project lifecycle stages, including requirements/needs gathering, data transformation/processing, training & compiling models for specific set of EDGE hardware, and building inference engine to infer those models on those EDGE hardware.
- Define AI/ML reference architectures, technology stacks, and design/implementation best practices as they apply on EDGE hardware.
- Research, experiment and rapidly build prototypes and POCs using open source AI/ML tools and platforms.
- Implement, tune, and integrate pre-trained models, and leverage transfer learning where applicable.
- Set up end-to-end IoT video/audio data ingestion, processing, and AI/ML inference pipelines on EDGE hardware.
- Author technology/solutions/services white papers, medium blogs and sales briefs.
You’ll Need To Have
- Bachelors, Masters or PhD. or equivalent in Computer Science, Computer Engineering, or related field.
- One or more years of experience as an ML/AI engineer with a strong focus on computer vision or Natural Language processing.
- Experience with AI/ML frameworks and libraries such as TensorFlow, PyTorch, MxNet, TFLite, CUDA, cuDNN etc.
- Experience with computer vision DNNs: e.g. R-CNNs, SSDs, Yolo, Resnet, MobileNet
- Experience with writing/editing model layers from research papers.
- Experience in AI/ML model optimization tools such as NVIDIA TensorRT, Intel OpenVino, ONNX Runtime, TVM etc.
- Experience with video ingestion and processing pipeline such as Gstreamer.
- Experience with edge IoT platform such as AWS IoT Greengrass, Azure IoT Edge.
- Experience in model containerization and deployment using container systems such as Docker, Kubernetes, AWS ACS/AKS, etc.
- Experience in quick model prototyping using Jupyter Notebooks.
- Experience in Cloud based AI/ML platforms such as AWS Sagemaker, Azure ML.
- Experience in one or more of these programming languages: Python, C, C++.
- Experience with ML/AI serving/inference platforms such as Tensorflow Serve, NVIDIA Triton.
- Experience with deploying and serving models on EDGE devices, at-least from one of these EDGE hardware and not limited to Raspberry Pi, Android, NVIDIA Jetson, Intel Movidius, Qualcomm etc.
Preferred Qualifications
- Excellent oral and written communications skills.
- Good understanding model compiler frameworks: TVM, MLIR, GLOW etc.
- Good Leadership skills to lead team of Junior engineers and interns.
We are headquartered in Pune.
Submit CV To All Data Science Job Consultants Across Bharat For Free