Back to jobs
Ifm-Us

Research Engineer/Scientist - Speech/Audio Machine Learning

Paris

Pay
Pay not listed
Work setting
On-site — work setting source
Work setup in the employer’s posting: onsite
From the employer’s posting
Employment
Full-time — employment source
Employment type Full-time
Employment type in the employer’s posting: Full-time
From the employer’s posting
Check the employer’s page ↗

What you’ll work on

Full posting

  • Develop novel neural architectures for low-latency speech-to-speech translation and generation

  • Design custom objective functions to optimize prosody, intelligibility and naturalness

  • Run large-scale training runs and ablation studies on architecture and tokenization

  • Build internal benchmarks using objective metrics and human MOS testing

From the employer’s posting
Develop novel neural architectures for low-latency speech-to-speech translation and generation
Design and implement custom objective functions to optimize prosody (emotions, intelligibility, naturalness).
Conduct large-scale training runs, performing ablation studies on model architecture and tokenization strategies.
Establish rigorous internal benchmarks using both objective metrics (WER, MCD) and subjective human-in-the-loop (MOS) testing.

What you’ll bring

All qualifications

Core experience

  • PhD or MSc in Computer Science, focused on Deep Learning, Signal Processing, or Computational Linguistics
  • Published research in top-tier venues such as NeurIPS, ICLR, ICASSP, or Interspeech
Qualification wording
PhD or MSc in Computer Science with a focus on Deep Learning, Signal Processing, or Computational Linguistics.
Published work in top-tier venues (NeurIPS, ICLR, ICASSP, Interspeech).
Education & alternatives
Qualifications - PhD or MSc in Computer Science with a focus on Deep Learning, Signal Processing, or Computational Linguistics. - Record of Research: Published work in top-tier venues (NeurIPS, ICLR, ICASSP, Interspeech).

About Ifm-Us

We are a dedicated research lab for building, understanding, using, and risk-managing foundation models.

In the employer’s words · Read in context

Posting record

Report an error

Open 6 monthsWe first saw this posting 200 days ago and it is still up. Roles open this long are often slow to fill or kept open to collect applications.

Status in our records
Live
First seen by us
Apr 15, 2026 · 200 days ago
Recorded sightings
140
Last seen by us
Nov 1, 2026
Employer says posted
Dec 30, 2025

These dates show when we found the posting. Check the employer’s website to confirm it is still accepting applications.

Your next step

Check the employer’s posting for the current role and application details.

Already applied? Track this application

Job description

View original posting ↗

About the Institute of Foundation Models 
 
We are a dedicated research lab for building, understanding, using, and risk-managing foundation models. Our mandate is to advance research, nurture the next generation of AI builders, and drive transformative contributions to a knowledge-driven economy.
 
As part of our team, you’ll have the opportunity to work on the core of cutting-edge foundation model training, alongside world-class researchers, data scientists, and engineers, tackling the most fundamental and impactful challenges in AI development. You will participate in the development of groundbreaking AI solutions that have the potential to reshape entire industries. Strategic and innovative problem-solving skills will be instrumental in establishing MBZUAI as a global hub for high-performance computing in deep learning, driving impactful discoveries that inspire the next generation of AI pioneers.
 
The Role
 
As a Research Scientist specializing in speech/audio machine learning, you will contribute to the design and training of SoTA end-to-end neural speech models. You will be responsible for developing the core intellectual property, moving beyond cascaded ASR → TTS systems toward native audio-to-audio multimodal architectures.

Key responsibilities

  • Architectural Design: Develop novel neural architectures for low-latency speech-to-speech translation and generation (e.g., Diffusion, Flow-matching, Transformer-based audio LLMs). 
  • Loss Function Engineering: Design and implement custom objective functions to optimize prosody (emotions, intelligibility, naturalness). 
  • Experimental Iteration: Conduct large-scale training runs, performing ablation studies on model architecture and tokenization strategies. 
  • Evaluation Frameworks: Establish rigorous internal benchmarks using both objective metrics (WER, MCD) and subjective human-in-the-loop (MOS) testing. 

Qualifications

  • PhD or MSc in Computer Science with a focus on Deep Learning, Signal Processing, or Computational Linguistics. 
  • Record of Research: Published work in top-tier venues (NeurIPS, ICLR, ICASSP, Interspeech). 

Employment type

Full-time

Source details

View original posting ↗

Source notes

Source excerpts

Selected passages from the saved posting. Check the full description for conditions and exceptions.

Pay

No pay amount identified in the saved description.

Location & working pattern

Paris

Working pattern and location restrictions need checking in the full posting.

Work authorization

No clear work-authorization passage found. Eligibility is unconfirmed.

Open source at jobs.lever.co ↗Read the full description ↓
AI answers unavailable

We couldn’t identify enough role detail in this saved description to support an AI answer. Read the full posting