AI Futures

machine learning engineer

In short

This senior machine learning engineer role, hybrid in Berlin, involves owning an end-to-end on-device audio ML pipeline for a clinical AI company building voice-based cardiac diagnostics. The company posting this is a medtech firm whose device holds EU Class IIa MDR approval and FDA Breakthrough Device Designation, working with a proprietary dataset of over three million labelled clinical voice samples. It requires 5+ years of ML engineering experience in audio/speech signal processing with production systems, on-device inference optimisation, strong Python/PyTorch or TensorFlow skills, and experience in regulated medical device development.

About
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.
Responsibilities
•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
Requirements
•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
Conditions
•€90,000 – €105,000 base + equity

Stop applying.
Get referred.

$10 in free credits

In just 60 seconds, fully on autopilot — Eraldt's AI agents read your CV, map the roles you fit, find live vacancies and the people who can refer you, write personal emails, and get you referred.

This isn't an application: your CV doesn't go to the company, and we don't promise a referral for this exact role.

Discover who else lands interviews on autopilot