Computer Vision Researcher

Nagish

4d•Hybrid

About The Position

As Computer Vision Researcher at Nagish, you will lead the development and deployment of models that power our video generation, sign language animation, transcription, and gesture segmentation efforts. You will collaborate across teams to build models that are indistinguishable from human interpreters and help scale our impact through automation and cutting-edge research. On a day to day, you will: Use and extend models for pose estimation, gesture segmentation, sign language animation, and transcription Integrate and champion a video generation pipeline that looks and feels like a human interpreter Evaluate, optimize, and deploy computer vision models to production Collaborate with the data engineer to build scalable training and inference pipelines Automate and accelerate CV tasks for annotation and content generation

Requirements

PhD in Computer Science, AI, or related field, or equivalent industry experience
3+ years working with PyTorch and computer vision models
Proven ability to take ML models from research to production
Solid understanding of machine learning, deep learning, optimization, and language models
Strong Python skills and experience integrating models into cloud environments

Nice To Haves

Experience working with motion or sign language data is a strong advantage
Publication record in top-tier computer vision or ML venues preferred

Responsibilities

Use and extend models for pose estimation, gesture segmentation, sign language animation, and transcription
Integrate and champion a video generation pipeline that looks and feels like a human interpreter
Evaluate, optimize, and deploy computer vision models to production
Collaborate with the data engineer to build scalable training and inference pipelines
Automate and accelerate CV tasks for annotation and content generation