AI Video Generation Consultant – ComfyUI / Wan / Kling / Short-Form Content

About the role We are looking for an experienced AI Video Generation Consultant to help us research, design and improve scalable workflows for creating original short-form social media content. This is primarily a technical consulting and R&D role. We want someone who deeply understands the current AI video ecosystem and can advise our team on the best tools, models, workflows and infrastructure for producing high-quality short-form video efficiently and at scale. What we need help with Designing scalable AI video generation workflows ComfyUI workflow architecture Image-to-video workflows Video-to-video workflows Character consistency across generated content Motion and pose control Reference-based generation techniques Improving realism and temporal consistency Creating natural smartphone-style social content Batch video generation API integrations and automation GPU/cloud infrastructure Generation speed and cost optimization Automated and human QA processes Comparing current AI video models and tools Tools / experience we're interested in Experience with several of the following would be ideal: ComfyUI Wan Kling Runway Google Veo LoRA training Diffusion models ControlNet / pose-control workflows Image-to-video models Video-to-video models Python APIs GPU/cloud infrastructure AI workflow automation We are particularly interested in people who understand the technical side of AI video generation, rather than only prompting consumer AI tools. What we're trying to accomplish Our goal is to understand how to build a repeatable system capable of producing large volumes of original short-form social media content while maintaining high visual quality. We want to determine: Which AI video models are best for different use cases How generation workflows should be structured How consistency can be improved How reference inputs can guide motion, composition and creative direction How workflows can be automated How generation costs can be reduced at scale Where human review should remain in the production process Ideal candidate You may be a good fit if you: Have hands-on experience building advanced AI video workflows Understand ComfyUI beyond basic templates Have experimented extensively with current video-generation models Understand the limitations of AI-generated video Can compare different technical approaches objectively Understand automation and scalable infrastructure Can clearly explain technical concepts Can show examples of workflows or systems you've previously built When applying Please send: Examples of AI video work you've created Examples of ComfyUI workflows you've built Which AI video models you currently consider strongest and why Your experience with image-to-video and video-to-video Your experience building automated or batch-generation systems A short explanation of how you would approach designing a scalable AI short-form video generation pipeline We're looking for someone who can consult with our team initially, with the potential for ongoing technical work if there is a strong fit.