Generative AI Engineer

About the job

We are looking for a Generative AI Engineer who can combine strong ML engineering with practical 3D generation knowledge. The ideal candidate should be comfortable working on diffusion-based generation systems, text-to-3D or image-to-3D workflows, asset validation pipelines, and scalable GPU inference systems. Key Responsibilities 1) AI Model Development • Research, evaluate, and implement state-of-the-art 3D generation models. • Build pipelines for text-to-3D asset generation. • Develop AI models capable of generating: • environments • structures • terrain • props • modular game assets • Improve quality, consistency, and usability of generated outputs for downstream game or simulation workflows. 2) Diffusion & Generative Systems • Build and optimize diffusion-based systems for: • 3D asset generation • mesh synthesis • texture generation • Evaluate, test, and integrate model ecosystems such as Tripo3D, Stable Diffusion 3D, Kaedim, and Scenario3D wherever relevant. • Fine-tune or adapt model pipelines for production-ready performance and better control over output quality. 3) Prompt-to-World Interpretation • Develop systems that convert natural language prompts into structured 3D scene specifications. • Design blueprint or schema-driven world definitions used to construct game environments. • Implement AI-driven layout reasoning for scene composition and greybox generation. • Bridge the gap between text prompts, generated assets, and final environment assembly. 4) Asset Validation & Pipeline Engineering • Validate generated assets for: • topology • mesh integrity • polygon count • game engine compatibility • Convert AI-generated assets into production-friendly formats such as GLB, FBX, and other engine-ready formats. • Build automated asset QA and optimization workflows to reduce unusable generations and improve production efficiency. 5) AI Infrastructure • Build scalable pipelines for: • GPU-based generation • batch asset generation • asset caching and reuse • Improve inference performance, resource usage, and pipeline scalability. • Collaborate with product, design, and engineering teams to integrate generation systems into a larger prompt-to-world platform. Required Skills • Strong hands-on experience with Generative AI and diffusion models. • Experience working with 3D generation models. • Strong proficiency in Python and ML frameworks such as PyTorch or TensorFlow. • Experience with text-to-3D or image-to-3D pipelines. • Good understanding of mesh processing and 3D graphics concepts. Preferred Skills • Experience with NeRF, Gaussian Splatting, or implicit neural representations. • Experience working with game engines. • Familiarity with CLIP embeddings for style matching. • Experience with GPU pipelines and model optimization. • Knowledge of procedural generation. Ideal Candidate Profile The right candidate is someone who can work across both research and engineering. They should be able to experiment with emerging generative AI approaches for 3D creation while also building robust, scalable systems that support real-world asset generation and environment assembly. They should understand model behavior, output quality, and the practical needs of engine-ready 3D workflows. This profile is a synthesis of the responsibilities and skills described in the source JD.

Requirements

• Generative AI
• ML Engineering
• 3D Generation
• Python
• Diffusion Models

Preferred Technologies

• Generative AI
• ML Engineering
• 3D Generation
• Python
• Diffusion Models