Lead AI Researcher, Text-to-Speech

Fixie.ai

Fixie.ai

Software Engineering, Data Science

Posted 6+ months ago

Research Engineer / Scientist, Speech Generation

About Fixie

We’re is a Seattle-based AI startup (with support for working remotely). We’ve raised $17M in seed funding. Our vision is simple: build artificial intelligences that can communicate as naturally as humans. We’re a small team of researchers and engineers with a deep focus in speech and real-time technologies. Our core model, Ultravox, is open-source. We also build a serving stack that’s optimized for very low-latency interactions.

The Role

As a Research Engineer & Scientist working on Speech Generation, you’ll lead the effort to improve speech generation for Ultravox, our OSS speech-to-speech model.

What you’ll do

Lead critical research on multi-modal input and output from LLMs, including voice and image encoders and decoders, for text-to-speech, speech-to-text, and speech-to-animation.
Train and improve voice and vision models based on public and proprietary data sources.
Review and improve our data flywheel.
Develop methods to improve efficiency, correctness, and quality of models.
Build tools to measure model quality and performance.

Things we’re looking for

An incredibly strong AI researcher with a track record of contributions to AI products and systems.
Experience with Large Language Models or other generative AI models.
Experience with speech or vision models.
Strong experience in Python and, ideally, PyTorch.
Ability to roll up your sleeves and get things done.
A great communicator and team player.

Benefits

Generous equity package
Unlimited PTO (take time when you need it)
Top-of-market salary
Great healthcare
401k with match

Apply

ALT