Deskripsi Pekerjaan
Are you passionate about leveraging artificial intelligence to make a tangible difference in patient care and clinical operations? Nanyang Technological University (NTU) is seeking a highly skilled and motivated Speech AI Engineer (Healthcare) to join our pioneering research and development team. In this role, you will be at the forefront of medical technology, transforming how healthcare professionals interact with clinical systems through advanced voice and speech technologies.
As part of this dynamic initiative, you will develop, optimize, and deploy cutting-edge Automatic Speech Recognition (ASR) and Natural Language Processing (NLP) models customized for clinical environments. Our mission is to significantly reduce the administrative burden on medical practitioners, allowing them to focus on what matters mostāpatients. You will work alongside world-class researchers, clinical partners, and software engineers in a highly collaborative, resource-rich ecosystem.
This position offers a unique opportunity to apply state-of-the-art Deep Learning techniques to real-world medical audio data, solving complex acoustic challenges unique to noisy clinical environments and diverse multilingual accents.
Tanggung Jawab
- Design, train, and fine-tune state-of-the-art Speech-to-Text (ASR) and Text-to-Speech (TTS) models tailored for healthcare-specific terminology and diverse accents.
- Develop and implement robust NLP pipelines to extract structured clinical insights from transcribed medical conversations.
- Collaborate closely with clinical stakeholders to understand workflow pain points and integrate speech solutions directly into electronic health record (EHR) systems.
- Optimize deep learning models for efficient, low-latency deployment on cloud infrastructure and edge devices.
- Maintain rigorous standards for medical data privacy, security, and ethical governance throughout the model lifecycle.
- Benchmark and evaluate the latest academic research in speech intelligence, rapidly prototyping new features to keep our clinical tools cutting-edge.
Kualifikasi
- Bachelorās, Masterās, or PhD in Computer Science, Data Science, Electrical Engineering, or a highly quantitative field with a specialization in Speech/Audio processing.
- Proven professional experience (2+ years) building and deploying Automatic Speech Recognition (ASR) or Natural Language Processing (NLP) systems.
- Proficiency in deep learning frameworks such as PyTorch or TensorFlow, along with speech libraries like Hugging Face (Transformers), Kaldi, ESPnet, or NVIDIA NeMo.
- Strong programming skills in Python and experience writing high-performance, production-ready code.
- Familiarity with medical informatics, clinical datasets, or healthcare standards is highly advantageous.
- Strong problem-solving abilities and a passion for developing technology with a positive societal impact.