data
Posted Apr 30Senior Machine Learning Engineer - Speech to Text
at Nabla Bio
Hybrid
You are nearing today's limit. Upgrade for unlimited access.
Responsibilities
- - Collaborate closely with product, ML, and infrastructure engineers to ensure speech systems integrate seamlessly into downstream note generation and agentic workflows.
Requirements
- Together with a community of clinician innovators, we’ve harnessed the best of machine learning science to develop Nabla: the leading AI assistant that’s restoring the human connection at the heart of healthcare.
- Backed by a recent $70M Series C, we’re hiring to build the next generation of clinical AI and improve the lives of clinicians and patients everywhere.
- This is a great time to join us! THE BEST OF AI AT THE SERVICE OF HEALTHCARE Nabla’s phenomenal traction is the result of years of rigorous product and ML development.
- Led by former Meta AI Research engineers, our team continuously pushes the frontier of speech and language AI in real-world clinical environments.
- Yann LeCun, Meta’s Chief AI Scientist and Turing award winner, is an advisor to Nabla.
- Our teams span machine learning, real-time audio processing, native desktop applications, and platform infrastructure to deliver AI into clinical settings reliably and at scale.
- As a Senior ML Engineer specialized in Voice AI, you will join a squad focused on speech and ambient intelligence, contributing end-to-end to the evolution of our real-time clinical audio stack.
- WHAT YOU’LL DO As a Senior ML Engineer specialized in Voice AI, you’ll play a key role in shaping the intelligence layer that powers Nabla’s assistant.
- Working alongside experienced ML engineers already building our speech stack, you’ll significantly contribute to advancing the systems that transforms the >1M hours of raw clinical audio flowing through our systems every month into reliable, structured input for our AI assistant.
- You will: - Contribute to the improvements of core components of our speech stack, including speech recognition, speaker diarization, voice activity detection (VAD), principal speaker detection, language detection and custom vocabulary.
- YOUR DNA We’re looking for a hands-on expert in speech and audio machine learning who combines research depth with production pragmatism.
- Requirements: - Deep expertise in speech and audio ML systems (5+ years), including
- experience with ASR, diarization, VAD, or multilingual speech models. - Strong understanding of real-time or streaming ML systems, with
- Experience working with transformer-based or hybrid speech architectures (e.g., wav2vec2, Whisper-like systems, conformers, etc.). - Solid knowledge of audio preprocessing, feature extraction, and robustness techniques. - Strong Python skills and
- experience deploying ML systems in production. - Ability to design and evaluate experiments with rigorous metrics tailored to speech systems (WER, DER, latency, robustness benchmarks). - Strong product mindset: you understand that improvements in speech quality directly impact clinician experience. - Fluent in English. Nice to have: -
- Experience with multilingual speech systems and language detection. -
- Experience in healthcare or other high-reliability domains. -
- Experience working on edge or resource-constrained inference environments.
- We come to work excited to leverage AI to do more for clinicians.
- We consistently look for ways to improve and do not shy away from doing the work to excel.
- Every day is a new chance to excel We aim for nothing less than the best and are willing to put in the effort and dedication required to exceed standards.
- Nabla does not accept unsolicited CVs from recruiters or employment agencies in response to the Nabla Careers page or a Nabla social media post.
- Any unsolicited CVs, including those submitted directly to hiring managers, are deemed to be the property of Nabla.
Benefits
- Together, we're committed to making clinicians' lives easier and improving healthcare experiences for everyone.
- We will never ask for the exchange of any money or credit card details during the recruitment process.
Contact
- If you’re contacted by a Nabla recruiter, please ensure whomever is contacting you truly represents Nabla and is utilizing a nabla.com http://nabla.com email address.
- You can find more information following this link https://consumer.ftc.gov/consumer-alerts/2023/05/scammers-are-hijacking-job-ads-heres-how-spot-fakes.
Additional details
- ABOUT NABLA We are a team of entrepreneurs, clinicians and engineers committed to bringing back joy to the practice of medicine.
- By streamlining clinical documentation, Nabla is helping clinicians focus on what matters most - patient care.
- We’re at the start of an ambitious journey: Ambient listening, dictation, coding, and command capabilities are all converging into a proactive assistant that intuitively streamlines clinical and financial workflows.
- We operate at scale, processing billions of tokens and thousands of hours of audio every week.
- ENGINEERING AT NABLA Engineering at Nabla is lean, fast-moving, and deeply technical.
- YOUR TEAM Product development at Nabla is led jointly by Engineering and Product and organized into cross-functional squads.
- Voice is the foundation of our product, enabling clinicians to interact directly with Nabla and capturing everything that happens during medical encounters.
- - Design and improve state-of-the-art speech systems, adapting modern architectures to real-world clinical environments (noisy rooms, overlapping speech, telehealth calls, and multilingual conversations).
- - Improve real-time performance, helping optimize streaming pipelines to balance latency, accuracy, and cost in live clinical workflows.
- - Increase robustness and reliability, ensuring consistent performance across accents, specialties, acoustic conditions, and healthcare organizations.