AI/ML Engineer – Generative AI Structural Variation POC

I am looking for an experienced AI/ML engineer to develop a small Proof of Concept (POC) for a private technical project. The goal is to test whether generative AI can perform controlled structural variation of a reference image. The system should take a base geometric reference image plus a natural-language instruction and generate multiple variations that modify structure, proportions, shapes, sections or construction while preserving the core geometry and identity of the original. This is NOT primarily about changing colors, textures or adding visual effects. The key challenge is controlled structural transformation. Relevant experience: - Generative AI - Computer Vision - PyTorch - FLUX / Stable Diffusion - ControlNet - IP-Adapter - Image-to-image - ComfyUI - Hugging Face Diffusers - Python For the first stage, I only need a technical POC, not a complete production application. The POC should demonstrate several outputs from the same reference image using different structural instructions. Budget: $200–250 USD for the initial POC. If the POC works successfully, there is potential for a larger follow-up project to develop the complete system and interface. I already have technical specifications and reference examples that can be shared privately after the initial discussion. When applying, please briefly explain your proposed technical approach, models/workflows you would test, and provide relevant examples of similar work.