Senior CV EngineerUrgent

We are looking for a Senior Computer Vision Engineer to train and fine-tune generative models, including text-to-image, image-to-image, video-to-image, and IP-Adapter models, for photorealistic and stylized visual output. You will work with image classifiers, rankers, and image or video captioning models, and help define a computer vision roadmap based on current research and open-source developments.

You will own the iterative model improvement and quality validation process, while optimizing inference through diffusion optimization, quantization, and framework-level improvements. We need someone with 5+ years of diffusion-model training experience, strong knowledge of the Diffusers and Transformers libraries, and hands-on IP-Adapter experience. Python, Go, or C# backend experience and scalable deployment knowledge are beneficial. Experience with flow matching, distillation, DPO, text-to-video, CLIP fine-tuning, multimodal LLMs, or NLP training is a plus.

Budget range:
Receive offers