Senior ML Engineer (Voice Products)

About the company

The goal of Denti.AI is to provide the best AI technology to dentistry, with a focus on revolutionizing radiological diagnostics, finding more pathologies earlier, and enabling more complete and accurate dental records.

Our software is designed to help dentists and dental teams work more efficiently and accurately while providing patients with the best possible care. We are constantly working to improve our software so that it can be used by even more dentists and dental team members around the world.

Denti.AI is backed by leading international investors in dental technology and led by a highly skilled and experienced team with advanced degrees in machine learning, oral and maxillofacial surgery, and computer science. With backgrounds serving on dental school and hospital faculties, managing fast-growing companies, closing multi-million dollar deals, leading large engineering teams in software development and R&D, and publishing the most cited research by a North American organization, this leadership team is well positioned to bring disruptive technology into the dental market.

Denti.AI is committed to providing innovative solutions that improve patient care and increase productivity for dental practices. The team’s deep understanding of the dental industry, coupled with their technical expertise, makes them uniquely qualified to develop products that will positively impact the profession.

Responsibilities

As a part of the team, you will be:

• Participating in crucial product decisions.
• Developing and improving models for audio/speech processing tasks.
• Integrating recent advancements in Gen AI into the medical domain.
• Analyzing and incorporating user feedback.
• Studying relevant scientific papers to bring the most advanced approaches to the product.

Required skills

• Experience in classic audio processing, speech recognition (ASR, STT), voice activity detection (VAD), denoising, intent parsing, speech synthesis, and others.
• Familiarity with public STT engines — DeepSpeech, Kaldi, Nemo & cloud providers.
• Python proficiency.
• Demonstrated history of deploying and maintaining models in production environments.
• PyTorch/TF & standard ML/DS stack proficiency.
• Model optimization and CPU inference experience.
• Fluency in both written and spoken English.
• Ability to rapidly experiment with hypotheses.
• Proficiency in Docker and wrapping your code in services.
• Tidiness and reproducibility in research.
• Aptitude for teamwork, including documentation, presenting results, handling customer feedback, and participating in code reviews.