Master Thesis: AI Receiver
Teknik, data och digitalt · Data, AI och analys · Maskininlärning · Artificiell intelligens · Datavetenskap
I korthet
Ericsson seeks a Master's thesis student to investigate AI receivers using neural networks and unsupervised online adaptation for changing wireless conditions. You will analyze field data, design and evaluate adaptation methods, and present findings to the research team.
Ansvarsområden
- Review research on online learning, self-supervised training, and domain adaptation for AI receivers.
- Analyze field-trial data to understand receiver performance across PxSCH configurations and channel conditions.
- Identify causes of performance degradation in AI receivers.
- Design, implement, and evaluate online adaptation methods.
- Assess receiver accuracy, link-level performance (BLER, throughput), adaptation speed, computational cost, and model stability.
- Present results and recommendations to the Ericsson research team.
Krav
- Background in electrical engineering, computer science, applied mathematics, or similar.
- Machine learning and deep learning (ANN, CNNs, training methodologies).
- Wireless communications fundamentals (OFDM, channel estimation, MIMO).
- Programming proficiency in Python (PyTorch, Jax or TensorFlow).
Önskade kvalifikationer
- Background in signal processing is a plus.
Förmåner
- Opportunity to use skills and imagination to push boundaries.
- Build solutions to tough problems.
- Be challenged in a diverse team of innovators.
- Opportunity to craft what comes next.
#AI#Receiver#Wireless