Creative AI Engineer - Image/Video Generation

ZeroSpace is a digital agency and production studio specializing in emerging technologies and real-time 3D for virtual production, CG animation, and immersive experiences. Our unique facility houses the largest fixed-install LED volume on the East Coast, industry-standard Vicon motion capture systems, and a state-of-the-art volumetric capture studio. We're an interdisciplinary team of technologists and artists where technical innovation meets creative vision. Our clients include major film studios, Oscar-winning directors, and the biggest brands in the world.

The Role

We're seeking a Creative AI Engineer to lead our exploration into AI-powered image and video generation for creative production workflows. You'll work directly with artists and creative technologists to implement the latest open-source generative AI models into our creative pipeline for use cases like style transfer, ControlNet guided generation, upscaling, brand-specific fine-tuning, and more. Our vision is that AI will augment and support the capabilities of creatives, allowing small teams to aim big. Together, we’ll push the boundaries of what's possible with AI in high-end narrative storytelling and commercial work.

In this role, you will

• Design and implement workflows for creative production using open-source tooling like ComfyUI
• Collaborate closely with artists and creative technologists to understand workflow requirements
• Integrate inputs from existing 3D production workflows as guidance for models
• Create LoRAs and fine-tunes for large image and video diffusion models, including dataset prep
• Implement video generation features into ComfyUI such as conditioning controls, noise injection, and video extension
• Work with image generation models such as FLUX and StableDiffusion
• Create utility scripts and nodes for data processing, file naming, and parameter tweaking
• Bridge the gap between cutting-edge AI research and practical production applications

About you

• In-depth practical experience with ComfyUI, such as custom node development
• Proven experience in object-oriented Python programming
• Proficiency with deep learning frameworks such as PyTorch or TensoFlow
• Experience fine-tuning diffusion models
• Familiarity with modern video generation models (WAN, Hunyuan, LTXV, MAGI-1, etc.)
• Familiarity with modern image generation models
• Able to set, own, and communicate direction in a dynamic environment

Nice to Have

• Background in computer graphics or digital content creation
• Familiarity with Unreal Engine and 3D production pipelines
• Knowledge of color science and post-production workflows
• Experience with creating agentic systems