Our companies are made up of insanely talented people driven to change the world — and many of them are hiring. If you have drive, expertise, and a taste for adventure, we whole­heart­edly encourage your interest.

  • 72
    Companies Hiring
  • 2,425
    Open Roles

Applied Scientist Intern (Audio Model Interpretation)

Reality Defender

Reality Defender

Posted on Thursday, December 14, 2023
About Reality Defender
Reality Defender is a groundbreaking security platform offering comprehensive deepfake detection. A Y Combinator graduate, Comcast NBCUniversal LIFT Labs alumni, and backed by DCVC, Reality Defender's proactive deepfake and AI-generated content detection technology is developed by a leadership team with over 20 years of experience in applied research at the intersection of machine learning, data science, and cybersecurity.
With models defending against present and future fabrication techniques, Reality Defender is the best way to detect and deter fraudulent text, audio, and visual content, partnering with government agencies and enterprise clients to enhance security and detect fraud.
Role Overview
Reality Defender seeks an Applied Scientist Intern to build model interpretation and decision attribution algorithms for our Generative Audio Detection models.


  • Investigate saliency and activation mapping techniques on different forms of audio representations, e.g, spectrograms and acoustic features (pitch, formants, etc.)
  • Build insights for decision attribution on audio inputs, e.g., identify the most impactful segments within an audio towards a classification outcome
  • Prepare a custom interpretation library for our generative audio detection models
  • Propose novel end-to-end solutions and publish the research
  • Collaborate with scientists and engineers across the organization

About You

  • Currently enrolled in a PhD program in speech or audio processing, deep learning, or a related fieldImp
  • lemented and/or published peer-reviewed research papers in reputable AI research venues such as NeurIPS, ICLR, *ACL, Interspeech
  • Have 1+ years of hands-on experience with model interpretation tools, e.g., Grad-CAM, SHAP, etc.
  • Have 1+ years of programming experience in Python and model building in PyTorch, preferably for audio processing such as HuBERT, wav2vec, and related models
  • Team player with a positive attitude and good communication skills
  • Excited about our line of work and can start immediately