Senior Computer Vision Engineer

About the role

We are seeking a Senior Computer Vision Engineer to lead the development of next‑generation generative visual AI technologies. Based in Italy, you will work in a globally distributed team to design, train, and deploy high‑quality photorealistic and stylized image and video models.

Key responsibilities

• Train, fine‑tune and enhance generative CV models such as text‑to‑image, image‑to‑image, video‑to‑image and adapter‑based architectures.
• Develop and improve image classification, ranking and captioning systems for complex visual contexts.
• Monitor emerging research and open‑source advances, translating them into development roadmaps.
• Design and own model evaluation frameworks and quality validation processes.
• Optimize model inference using diffusion acceleration, quantization and framework‑level enhancements.
• Collaborate with ML teams to integrate advanced CV capabilities into broader AI systems.
• Contribute to multimodal AI projects that combine visual and language understanding.

Required profile

• 5+ years of experience with diffusion models, including training, fine‑tuning and architectural customization.
• Proven ability to drive research initiatives and turn experimental results into production‑ready solutions.
• Strong problem‑solving, analytical thinking and collaboration skills.
• Experience working in a distributed, collaborative environment.

Required skills

• Diffusion models and related techniques (e.g., flow matching, model distillation).
• Machine learning frameworks and libraries, especially Diffusers and Transformers.
• IP‑Adapters or similar conditioning techniques.
• Python programming and backend engineering for scalable deployment.
• Deep learning, generative AI and computer vision best practices.