Jobs Companies Oddin Research Scientist for Speech Synthesis

À propos de ce poste Research Scientist for Speech Synthesis chez Oddin

Oddin · Hybride · Valka.ai
About Valka
Valka, a visionary spin-off from the Realms Group (the parent company of Oddin.gg), is on a mission to revolutionize the way people create and experience digital content. Our team believes that content shouldn’t just be consumed; it should be co-created in real time, blurring the lines between imagination and reality. By harnessing the power of cutting-edge AI, we aim to build an interactive human-digital platform where virtual characters respond dynamically to each user’s voice, text, gestures, and more.
This is your chance to join a diverse group of innovators who are driven to redefine what’s possible in generative content. Together, we’re changing the paradigm from passive viewing to active participation, unlocking new creative frontiers across gaming, entertainment, education, and beyond.
 
Position Intro:
We’re looking for an experienced Aplied Research Scientist for Speech Synthesis for a foundational role to join our new team.
You’ll develop text-to-speech and voice cloning models to create synthetic voices for our avatars that sound like public figures.
We expect you to work with state-of-the-art models and push the limits of what voice cloning and TTS can do. This role requires a solid understanding of speech synthesis, NLP, and deep learning. Experience working with large text and speech datasets is highly desirable.
You’ll build efficient training and deployment pipelines for voice models. Part of your job will be designing validation strategies that compare synthetic speech to real recordings, and creating custom metrics to measure quality.
You’ll also help set up the infrastructure for tracking experiments, making results reproducible, and serving models in production. From training on distributed systems to monitoring deployed models, you’ll be involved in the full machine learning workflow.

What You will work on:

  • Design, develop, and optimize text-to-speech models with a focus on maintaining the style and authenticity of the original voice actors.
  • Collaborate with teams to work on audio datasets that include voice recordings and multilingual transcriptions.
  • Experiment with state-of-the-art architectures for speech synthesis, including neural TTS and voice cloning models.
  • Define robust validation strategies and implement custom evaluation metrics comparing synthetic vs. real gameplay.
  • Contribute to foundational MLOps practices and infrastructure; from experiment tracking, CI/CD, deployment, monitoring, and versioning.
  • Skills you need:

  • Solid experience with deep learning frameworks (PyTorch, TensorFlow, or JAX)
  • Understanding of audio processing (sampling, spectrograms, vocoders)
  • Experience with training text-to-speech, and voice cloning models
  • Familiarity with speech synthesis models such as WaveNet, Tacotron, and VITS
  • Worked with voice cloning models (e.g., XTTS, YourTTS, or similar)
  • Experience with transformers and diffusion models.
  • Ability to implement ideas from research papers
  • Understand machine learning and deep learning fundamentals
  • Strong programming skills and experience working with Python

  • Join us at Valka to lead a new wave of interactive audio content—one where your creativity and technical prowess will help transform entire industries and reimagine how digital content is created, shared, and experienced.
     
    By applying to this position, you consent to Valka.AI s.r.o., ID No.: 231 32 221, Pod dráhou 1637/6, Holešovice, 170 00 Praha 7, Czech Republic together with it's subsidiaries processing your personal data under Regulation (EU) 2016/679.
     
    Your data will be processed for recruitment and may be retained for up to 3 years for similar job opportunities.Rights: Access, correct, delete, restrict, or object to processing; withdraw consent via soulforge@valka.ai; or complain to www.uoou.cz.
    Prêt à postuler chez Oddin ?
    Postuler chez Oddin

    Emplois similaires

    OD
    Research Scientist, Text-to-Speech
    Oddin
    ⚡ Postuler tôt Valka.ai
    ● Nouveau 👁 Vu ✓ Postulé il y a 5 mois
    Snowflake
    Staff Research Scientist, Exotic AI
    Snowflake
    ⚡ Postuler tôt US-WA-Bellevue Hybride $236,000–$339,200
    ● Nouveau 👁 Vu ✓ Postulé il y a 2 h
    Apolloresearch
    Research Scientist/Engineer (Evaluations)
    Apolloresearch
    ⚡ Postuler tôt London & San Francisco Sur site
    ● Nouveau 👁 Vu ✓ Postulé il y a 3 h
    SA
    Staff Materials Research Scientist, PFAS Alternative Discovery
    SandboxAQ
    ⚡ Postuler tôt United States Télétravail $163,200–$306,000
    ● Nouveau 👁 Vu ✓ Postulé il y a 4 h
    Samsung Research America
    Principal Research Scientist, Robotics
    Samsung Research America
    ⚡ Postuler tôt 665 Clyde Avenue, Mountain Vie... Sur site $242,500–$376,650
    ● Nouveau 👁 Vu ✓ Postulé il y a 6 h
    Anduril Industries
    Research Scientist, Battlespace Awareness
    Anduril Industries
    ⚡ Postuler tôt Broomfield, Colorado, United S... Sur site $165,000–$218,000
    ● Nouveau 👁 Vu ✓ Postulé il y a 6 h
    Anduril Industries
    Research Scientist, Battlespace Awareness
    Anduril Industries
    ⚡ Postuler tôt Broomfield, Colorado, United S... Sur site $126,000–$167,000
    ● Nouveau 👁 Vu ✓ Postulé il y a 6 h
    Anduril Industries
    Research Scientist
    Anduril Industries
    ⚡ Postuler tôt Broomfield, Colorado, United S... Sur site $126,000–$167,000
    ● Nouveau 👁 Vu ✓ Postulé il y a 6 h
    SA
    Manager, Research Scientist
    Scale AI
    ⚡ Postuler tôt San Francisco, CA; New York, N... Sur site $290,400–$363,000
    ● Nouveau 👁 Vu ✓ Postulé il y a 7 h

    Inscrivez-vous pour des suggestions adaptées aux emplois que vous ouvrez et aux recherches que vous enregistrez.

    Plus d’emplois chez Oddin

    Voir tous les emplois chez Oddin →

    Postuler maintenant
    🤖

    Doucement — un instant

    JobsRadar a été conçu pour de vraies personnes qui traversent une période difficile dans leur recherche d’emploi — pas pour des requêtes automatisées. Vous cliquez beaucoup trop vite et vous êtes maintenant temporairement bloqué.

    Revenez plus tard. Si vous cherchez réellement un emploi, nous sommes de votre côté — agissez simplement comme un être humain.

    Catch your next role the second it’s posted.

    Create a free account and we’ll watch the boards for you — the instant a job matches your search, it lands in your inbox or Telegram. No digging, no refreshing.

    Create free account

    Free forever · takes 30 seconds · already have one?

    Prenez une longueur d’avance dans votre recherche d’emploi.

    Rejoignez notre canal Telegram pour ce qui vous aide à décrocher le poste — références salariales, le pouls hebdomadaire du marché et les annonces de nouveautés. Pas de spam, que du signal.

    Rejoindre le canal — c’est gratuit