Чтобы адаптировать резюме под вакансию или составить сопроводительное письмо, загрузите резюме
описание
AI Futures supports a search for a clinical AI company developing voice-based medical diagnostics. The company has built a large dataset of clinical voice recordings for cardiac conditions, and its core device has received EU Class IIa MDR approval and FDA Breakthrough Device Designation.
задачи
Own the end-to-end on-device audio ML pipeline, from acoustic feature extraction and model training to quantisation, optimisation, and deployment on consumer mobile hardware without cloud dependency
Develop and iterate on model architectures for short-duration, variable-quality clinical audio using a proprietary dataset of over three million labelled voice samples from cardiac patients
Design and implement evaluation frameworks that reflect real-world clinical performance, including robustness to recording environments, device variation, background noise, accents, and patient population diversity
Work within the regulated medical device development process, including versioned models, documented validation, audit trails, and engineering requirements for MDR and FDA submissions
Collaborate with the clinical team to understand the physiological signal and ground model development decisions in clinical evidence
Contribute to the technical roadmap as the algorithm expands to additional cardiac biomarkers and potentially other disease areas
требования
5+ Years of machine learning engineering experience focused on audio, speech, or acoustic signal processing, with production systems rather than research prototypes
Hands-on experience with on-device or edge ML inference, including model quantisation, pruning, and optimisation for constrained hardware
Strong Python and deep learning framework expertise (PyTorch or TensorFlow)
Experience with audio libraries such as librosa, torchaudio, or comparable tools
Rigorous approach to model evaluation, including sensitivity, specificity, ROC/AUC, and statistical requirements of clinical validation
Experience working in or alongside a regulated environment where engineering decisions have auditable consequences
.svg)
