PHY Algorithms Senior Engineer - AI/ML - Parallel Wireless

3+ years of hands-on experience with deep learning frameworks (PyTorch, TensorFlow, or similar) and neural network architectures (CNNs, RNNs, transformers, autoencoders). Familiarity with model optimization techniques for real-time deployment: quantization, pruning, knowledge distillation, and hardware-aware neural architecture search. An independent problem solver with excellent mathematical and analytical skills. Eager to learn and develop your professional skills in the fields of wireless communications and applied machine learning. Team player: Excellent communication skills, and ability to thrive in a global multi-site environment. Experience applying ML/DL to physical layer problems (e.g., channel estimation, MIMO detection, CSI feedback, learned codebooks, or end-to-end learned communication systems) - Advantage. Experience in PHY algorithms development for wireless modems - Advantage. Good understanding of the cellular standards (LTE/NR) - Advantage. Experience with ONNX Runtime, TensorRT, or similar inference engines - Advantage. M.Sc / PhD in electrical engineering (major in communication theory and systems, signal processing, and/or machine learning - Advantage).

Conduct algorithmic research, balancing performance, implementation cost, real-time constraints, and time-to-market, with a strong focus on ML-based approaches for PHY layer processing. Design and train neural network models for PHY tasks such as channel estimation, signal detection, beamforming, and decoding, targeting real-time inference on embedded platforms. Develop algorithms from initial research and simulation through to official customer releases, including literature reviews, ML model prototyping using Python, PyTorch, and TensorFlow, MATLAB modeling, specification writing, and support throughout implementation and end-to-end integration. Evaluate and benchmark ML-based solutions against traditional DSP approaches, considering accuracy, latency, computational cost, and overall system performance.

3+ years of hands-on experience with deep learning frameworks (PyTorch, TensorFlow, or similar) and neural network architectures (CNNs, RNNs, transformers, autoencoders). Familiarity with model optimization techniques for real-time deployment: quantization, pruning, knowledge distillation, and hardware-aware neural architecture search. An independent problem solver with excellent mathematical and analytical skills. Eager to learn and develop your professional skills in the fields of wireless communications and applied machine learning. Team player: Excellent communication skills, and ability to thrive in a global multi-site environment. Experience applying ML/DL to physical layer problems (e.g., channel estimation, MIMO detection, CSI feedback, learned codebooks, or end-to-end learned communication systems) - Advantage. Experience in PHY algorithms development for wireless modems - Advantage. Good understanding of the cellular standards (LTE/NR) - Advantage. Experience with ONNX Runtime, TensorRT, or similar inference engines - Advantage. M.Sc / PhD in electrical engineering (major in communication theory and systems, signal processing, and/or machine learning - Advantage).