We are seeking several Full Stack Engineers to build end-to-end AI-powered image and video production systems. In this role, you will work across frontend, backend, model integration, media processing, and product workflows to create tools that help users generate, edit, manage, and publish high-quality visual content.

You will work with modern AI models and multimodal systems, including image generation models, video generation models, and large language models such as Seedream, Gemini, Seedance, and other emerging image/video models. Your work will involve turning model capabilities into reliable product experiences, from prompt input and asset management to generation orchestration, preview, editing, export, and delivery.

This role is a strong fit for engineers who enjoy building complete products, care about both user experience and system reliability, and are excited about the future of AI-driven content creation. If you are familiar with video creation workflows, short-form content production, or editing tools such as CapCut/Jianying, that product intuition will be especially valuable.

Key Responsibilities：

Work with product managers, designers, and engineering teams to design and deliver scalable full-stack product features for AI image and video creation.

Build intuitive frontend experiences for prompt creation, image/video generation, storyboard editing, asset preview, media management, and export workflows.

Design and implement backend services, APIs, databases, task queues, and workflow orchestration systems that support reliable image/video production at scale.

Integrate and evaluate AI models such as Seedream, Gemini, Seedance, and other image/video generation models, turning model APIs and capabilities into stable product features.

Build end-to-end media pipelines, including prompt processing, model invocation, asynchronous task tracking, asset storage, metadata management, video rendering, transcoding, and delivery.

Collaborate with algorithm/model teams to improve prompt strategies, model selection, generation quality, latency, cost, and failure handling.

Develop responsive, performant, and maintainable web applications using modern frontend frameworks and component-based architecture.

Write clean, functional, well-tested code across frontend and backend systems, and troubleshoot, debug, and upgrade production features.

Create secure and reliable data flows for user assets, generated media, project files, and model-related metadata.

Improve product quality through automated testing, observability, performance optimization, error tracking, and production monitoring.

Write technical documentation for APIs, architecture decisions, media workflows, model integration, and operational processes.

Stay up to date with new AI models, video creation workflows, full-stack technologies, and industry best practices, and proactively apply them to product development.

Requirements：

Bachelors in Computer Science, Software Engineering, Information Technology, or related fields.

Proven experience as a Full Stack Engineer, Full Stack Developer, or similar role, with experience delivering production-grade web applications.

Strong frontend development skills with JavaScript/TypeScript and modern frameworks such as React, Next.js, Vue, or similar technologies.

Strong backend development skills with one or more languages such as Node.js, Python, Go, Java, or similar technologies.

Experience designing client-side and server-side architecture, building well-structured APIs, and developing scalable applications.

Familiarity with databases and storage systems such as MySQL, PostgreSQL, MongoDB, Redis, object storage, or similar technologies.

Solid understanding of HTTP, RESTful APIs, authentication, authorization, caching, asynchronous processing, and common web application architecture.

Ability to work across the full software development lifecycle, from product concept and technical design to implementation, testing, deployment, and production support.

Strong product sense, attention to detail, problem-solving ability, and willingness to understand real user workflows.

Excellent communication and teamwork skills, with the ability to collaborate effectively with product, design, engineering, QA, and algorithm/model teams.

Fluent in Mandarin Chinese.

Nice to Have：

Experience building AI-native products, AIGC tools, creator tools, media platforms, video editing products, or workflow automation systems.

Hands-on experience with image generation, video generation, multimodal models, LLM APIs, prompt engineering, model evaluation, or model orchestration.

Familiarity with Seedream, Gemini, Seedance, or similar image/video generation models and their practical product integration challenges.

Experience with media processing technologies such as FFmpeg, OpenCV, WebCodecs, Canvas, WebGL, WebGPU, or browser-based video rendering.

Familiarity with video editing workflows, timeline editing, storyboard creation, shot planning, asset libraries, subtitles, transitions, filters, or template-based video production.

Experience using video editing tools such as CapCut/Jianying, Premiere Pro, Final Cut Pro, DaVinci Resolve, or similar creative tools.

Experience designing asynchronous generation systems, distributed task scheduling, queue-based workflows, long-running jobs, retry mechanisms, and status polling.

Experience with performance optimization for frontend rendering, backend services, media processing, or model invocation cost and latency.