Generative AI Engineer – Video & Animation

The Role

We are looking for an Generative AI Engineer to develop AI-powered image and video generation systems. You will work on state-of-the-art diffusion and video generation models, helping improve quality, realism, temporal consistency, and generation speed while collaborating closely with AI researchers and systems engineers.

Responsibilities

• Develop and optimize AI-powered image and video generation pipelines.

• Fine-tune and evaluate diffusion and video generation models.

• Improve animation quality, temporal consistency, and rendering performance.

• Build tools for training, inference, evaluation, and content generation.

• Research and implement the latest advances in generative AI and animation.

• Collaborate with systems engineers to optimize inference performance.

Minimum qualifications

• Bachelor's or Master's degree in Computer Science or a related field.

• 3+ years of software engineering experience in the field of AI-ML based text and video generation.

• Strong proficiency in Python and PyTorch.

• Experience with diffusion models or modern generative AI frameworks.

• Strong problem-solving and software engineering skills.

Preferred qualifications

• Experience with image and video generation models such as SDXL, FLUX, Wan, Hunyuan Video, LTX Video or similar.
  
  

• Hands-on experience with generative AI workflows and tools such as ComfyUI, Forge, Hugging Face, or custom inference pipelines.
  
  

• Experience with LoRA training, ControlNet, fine-tuning, prompt engineering, and optimizing GPU-accelerated inference pipelines.