Role: Generative AI EngineerLevel: Mid/SeniorType: Full-time / Part-timeLocation: RemoteThis is a fully remote role. We accept applicants from all countries.About the RoleWe are seeking a Generative AI Engineer who specializes in high-fidelity image synthesis and transformation. you will be building production-ready pipelines that take existing visual data and enhance it using the latest open-source models. Your focus will be on precision, consistency, and professional-grade quality.What You’ll DoAdvanced Pipeline Development: Design and maintain complex ComfyUI workflows for high-resolution image-to-image transformations.Model Orchestration: Specialize in Qwen-Image-Edit (MMDiT) and Stable Diffusion (SDXL/Flux) architectures to achieve state-of-the-art results.Fine-Tuning & Adaptation: Implement and weight LoRAs effectively to maintain character, style, or architectural consistency. Sampling Optimization: Master KSampler configurations, selecting the right samplers.Natural Language Prompting: Leverage Qwen’s multimodal capabilities to translate complex natural language requests into precise visual edits.Technical RequirementsComfyUI Mastery: Ability to build stateful, modular workflows from scratch (Custom nodes, API integration, X/Y plotting).Model Expertise: Deep understanding of Qwen-Image-Edit-2511/2512 and the Stable Diffusion ecosystem.Sampling & Latents: Expert knowledge of denoise strength, noise schedules, and latent-space manipulation.Prompt Engineering: Proficiency in both "tag-based" prompting (SD) and "instruction-based" natural language prompting (Qwen/LLM-based CLIP).Measurement Pipelines: Develop Computer Vision algorithms to extract real-world dimensions (meters/cm) from 2D images using perspective correction and reference objects.