About the role:
CubiCasa is redefining the global real estate market by turning static imagery into dynamic property intelligence. We are seeking a Generative AI Engineer to bridge the gap between SOTA academic research and the high-volume reality of the market. You will architect systems capable of high-resolution synthesis, complex inpainting, and structural conditioning, processing tens of thousands of images daily with strict adherence to perspective and consistency. If moving beyond API wrapping to build the future of automated visual transformation is your thing, you come to the right place!
Â
Key Responsibilities:
- Workflow Orchestration: Design and implement modular inference pipelines using Stable Diffusion and Flux architectures.
- Complex Chaining: Utilize tools like ComfyUI or custom Python backends to chain non-linear workflows together.
- Geometric Conditioning: Implement and fine-tune SOTA preprocessors to ensure truthfulness and structural integrity.
- Inpainting & Outpainting: Develop robust algorithms for removing objects and generating coherent backgrounds.
- Style Transfer & Adaptation: Train and maintain a library of adapters to create models toward specific high-value aesthetic styles and lighting conditions.
- Semantic Segmentation: Integrate SOTA segmentation models to automatically identify specific image regions for targeted processing.
- Automated Quality Scoring: Develop scoring systems to detect hallucinations, artifacts, or perspective failures before human review.
Â
Qualifications:
- MSc/PhD in Computer Science, AI, Computer Vision, or equivalent practical experience.
- 3+ years in Deep Learning/Computer Vision, with at least 1 year focused specifically on Generative AI / Diffusion Models.
- Mastery of Python and PyTorch; proficiency with the Hugging Face ecosystem (Diffusers).
- Generative Stack: Deep technical understanding of Latent Diffusion Models.
- Excellent prioritization skills, analytical and problem-solving.
- Strong communication and presentation skills.
- Resourceful, ability to work independently while balancing being part of a team.
- Ability to use Gsuite tools in their work.
- A strong portfolio of personal projects demonstrating your AI/ML skills (e.g., GitHub repositories, publications, conference presentations) is highly desirable.
Â
Bonus points
- Vision specialists with strong generative experience.
- Experience working in domains where truthfulness and structure are critical (e.g., architectural visualization, industrial simulation).
- Experience creating custom nodes for ComfyUI or contributing to open-source generative AI projects.
Â
At CubiCasa, we offer you
- A meaningful and cutting-edge mission statement: We will empower the world to attach a Floor Plan on every listing.
- All the tools needed to do your work including compute resources with access to high-end infrastructure (H100/H200/B200 clusters) for training and experimentation.
- A dynamic and a supportive workplace for tomorrows superstars.
- The flexibility to choose when and where you work, so you can shape your work in the way that fits you best, but we still hope to see you from time to time at our office in Helsinki or Oulu.
- Competitive salary with attractive package of benefits incl. lunch, well-being, bike benefit
- Wide healthcare service
Â
How to Apply
Please send your resume and a cover letter explaining, why you are the ideal candidate for this position via this link: https://careers.cubi.casa/jobs/6847342-generative-ai-engineer
Apply at the latest on Sunday January 4th, 2026.
Â
Join us in shaping the future of virtual home touring. We look forward to hearing from you!