Edensign · 5 months ago
Lead Generative AI Engineer (Diffusion Models, 3D, VLM)
Boston, MA
Full-time
Onsite
Senior Level, Lead/StaffEdensign is building the future of AI-powered visual and spatial design, creating next-generation intelligent systems that merge generative AI with 3D understanding. They are seeking a senior technical leader to drive the development of their core AI engine, focusing on training large generative models and overseeing the evolution of their spatial AI stack.
Real Estate
Hiring Manager
George Zheng
Responsibilities
Design, train, and optimize cutting-edge generative models, including diffusion, 3D reconstruction, and multimodal/VLM architectures
Build and manage scalable training pipelines, data curation workflows, and experiment tracking
Lead research experiments, benchmarking, and exploration of new modeling techniques
Architect the evolution of our spatial AI stack—from prototyping new ideas to deploying production-ready models
Collaborate with engineering and product teams to integrate AI capabilities seamlessly into real-world workflows
Make strategic decisions around infrastructure, GPU utilization, model efficiency, and training optimization
Contribute to Edensign’s long-term technical roadmap and innovation direction
Qualification
Required
Strong expertise in training generative models (diffusion, GANs, 3D generative models, or scene-reconstruction networks)
Deep background in Computer Vision, Computer Graphics, 3D geometry, NeRF-like architectures, or multi-view learning
Experience with VLMs, multimodal models, grounding, or spatial reasoning is highly valuable
Proficiency in Python and modern ML frameworks
Hands-on experience with distributed training, GPU optimization, and large-scale experiment management
Ability to work independently and lead technical direction in a fast-paced startup environment
Strong analytical, problem-solving, and system design skills
Excellent communication and collaboration skills
Master's or PhD in Computer Science, AI/ML, Computer Vision, or a related field
Preferred
Familiarity with node-based generative tools (e.g., ComfyUI) is a plus
Experience in real estate, architecture, spatial design, or spatial computing is a bonus
Proficiency in Mandarin is preferred
Company
Edensign
Edensign is a cutting-edge virtual staging solution that empowers real estate professionals and designers to showcase properties in their best light.
2-10 employees
Funding
Current Stage
Early StageCompany data provided by crunchbase