Research Internship - Time-synchronous Speech LLMs

Société : Blynt AI

At Blynt, we are building the interface of the future: voice that works. Our team previously built Sonos Voice Control, delivering a production-grade voice experience to millions of users worldwide while pushing the technical boundaries, with a fraction of the resources of Big Tech and running the entire AI stack directly on Sonos speakers under extreme runtime and optimization constraints.

We focus on everything that happens between the microphone and the AI agent: turning raw, continuous audio into structured, real-time events that downstream systems can act on. Our model stack spans real-time transcription and turn-taking, with environmental and paralinguistic understanding on the roadmap. Powering the next generation of real-world agentic interactions, from robots to wearables and beyond, requires a step change in the underlying technology. That's what we're building.

Description du poste

As a Research Intern in our Audio & Speech Research team, you will explore state-of-the-art audio architectures and study how to apply them to our production . This is not a pure research role where papers are the output. You will design, train and evaluate models that run in real-time. You'll work at the intersection of research and engineering, translating state-of-the-art ideas into systems that work reliably in the real world.

Profil recherché

First and foremost, we're looking for kind and curious people who are genuinely excited about what we're trying to do: make a real dent in the conversational AI landscape. The list below isn't a checklist. Few candidates will meet every criterion, and we'd rather hear from people with a wide range of backgrounds and experience.

- Final-year MSc student in Machine Learning
- Proficient in PyTorch (or an equivalent deep learning framework)
- Comfortable writing production Python code, not just research prototypes
- Deep knowledge of Machine Learning fundamentals. Plus knowledge of recent architectures like the Transformer.
- Strong communication skills, fluent in English