Save application

mirelo

Dec 03

Research Scientist - Model Team

Remote Remote · Berlin

gopytorch researchfulltime

ashby

Match & cover letter

Create a profile to see your match and get a cover letter for this role.

Create profile and match

Job description

You will develop and train multimodal generative models for audio at Mirelo in Berlin. This role involves hands-on research and collaboration across teams to enhance audio generation capabilities.

Details

  • Berlin, remote work available
  • Competitive salary and equity offered
  • Experience in training large-scale generative models required
  • Skills in PyTorch and distributed training techniques needed

The work

  • Design and implement large-scale multimodal generative models for audio generation
  • Explore new modeling ideas for music, sound, and speech generation
  • Conduct ablation studies and communicate insights to the team
  • Contribute to all stages of model development including data curation and deployment