Responsibilities: — Train and fine-tune generative models: text2image, image2image, video2image, IP-adapters — Work with image classifiers, rankers, and image/video captioning — Research and implement current approaches from CV and open-source — Build a process for continuous improvement and model quality assessment — Optimize inference: diffusion optimization, quantization, kernels/framework-level optimization — Optionally, work with multimodal models at the intersection of CV and NLP

Requirements: — 5+ years of experience with diffusion models and their architectures — Solid experience with Diffusers, Transformers, IP-adapters — Experience with backend development in Python / Go / C# and scalable deployment will be a plus

📩 Apply / details — @That_is_sofia