Senior Member of Technical Staff (Video Generation & 3D, Cockpit Themes)

About Company

Founded in 2022, XG Tech is driving the future of smart vehicles. Its mission is to empower the digital transformation of automobiles, moving from distributed computing to a centralized, cross-domain platform.

XG Tech focuses on the intelligent cockpit—the next frontier of differentiation—while seamlessly integrating advanced driving systems. By reimagining cars as mobile living spaces, XG Tech aligns with the evolving trend of vehicles becoming the “third living space.”

Role Summary

As a Generative AI Research Engineer, you will research and develop generative models and pipelines for creating 3D scenes, video, and visual assets for next-generation intelligent cockpit systems. You will work on 3D generation, video synthesis, and AI-driven content creation, optimizing generated assets for visual quality, consistency, and real-time performance. You will also integrate generative outputs into production-ready 3D environments, ensuring they can be efficiently rendered and deployed on automotive hardware to deliver personalized and immersive in-car experiences.

Key Responsibilities

• Research and productize video generation and 3D asset generation for in-cabin themes: background sets, sky, ground, surroundings, and lighting that hold up inside a real Unity/vehicle environment.
• Own quality where it counts: generation success rate and consistency, not just visual plausibility in isolation — assets have to compile, integrate, and run in the final scene without a human fixing each one.
• Build and tune the generation pipeline, including quality gates that automatically reject what will not survive integration, and feedback loops that tell you why.
• Push feasibility work on harder directions (video rendering, self-vehicle models) from an open research question to a clear risk judgement with a recommendation attached.
• Improve throughput and cost: the pipeline has to produce sets of assets at production scale, not one hero image at a time.
• Work with designers and engineers on the loop from prompt to preview to production asset, and keep the taste barrier intact as the volume rises.

How you will stand out

• Strong academic background in Generative AI, Computer Graphics, Computer Vision, 3D Vision, or a related field, with a PhD or equivalent research experience preferred。
• Hands-on experience developing generative models and pipelines, particularly in diffusion models, video generation, 3D generation, or neural rendering.
• Strong understanding of 3D scene synthesis, visual consistency, lighting, materials, and asset generation, with the ability to optimize generated content for real-world applications.
• Experience implementing and optimizing generative AI workflows to produce high-quality, consistent, and scalable visual outputs.
• Demonstrated research or engineering achievements through publications in relevant conferences such as CVPR, ICCV, or SIGGRAPH, as well as shipped generative AI products, technical competitions, or production-scale generation pipelines.
• Strong visual and analytical skills, with the ability to identify quality issues in generated scenes and systematically improve model outputs through experimentation and optimization.

Nice to have:

• Experience with real-time 3D engines such as Unity or Unreal Engine, including integrating generated assets into interactive environments.
• Experience in material and emission generation, sky and terrain synthesis, 3D asset optimization, or mesh decimation.
• Familiarity with visual quality assessment, automated scoring metrics, and human-preference evaluation for generative models.
• Experience optimizing 3D assets and generative workflows for real-time rendering and deployment on resource-constrained automotive hardware.

XG Tech is committed to providing equal employment opportunities by country, state, and local laws. XG Tech does not discriminate against employees or applicants based on conditions such as race, color, gender identity and/or expression, sexual orientation, marital and/or parental status, religion, political opinion, nationality, ethnic background or social origin, social status, disability, age, indigenous status, and union.