Founding AI Agent Engineer (AI Video & Short Drama Generation)
About the Role
We are building a next-generation AI video and short drama creation platform for global creators. Users can provide a simple idea, story, novel, or script, and our multi-agent system automatically transforms it into a fully produced video through script planning, storyboard generation, character creation, video generation, voice synthesis, and post-production.
Responsibilities
AI Agent & Workflow Systems
- Design and develop production-grade Multi-Agent systems that power end-to-end AI video and short drama generation workflows, from ideation and script planning to storyboarding, video generation, voice synthesis, and final content delivery.
- Build scalable Agent Orchestration Frameworks capable of task decomposition, agent collaboration, memory management, context management, and autonomous execution.
- Develop workflow engines supporting DAG scheduling, asynchronous execution, long-running tasks, state persistence, checkpoint recovery, retry mechanisms, and resource allocation.
Multi-Modal AI Infrastructure
- Build a unified Model Routing Layer integrating leading multimodal models across text, image, video, and audio generation.
- Dynamically optimize model selection based on content type, shot requirements, quality, latency, and cost considerations.
- Develop Tool Calling, Function Calling, Memory Management, and Agent Runtime capabilities to improve agent autonomy and task completion quality.
AI Video & Short Drama Production
- Design systems that support the complete AI short-drama production pipeline, including script decomposition, scene planning, storyboard generation, character and asset management, video generation, dubbing, sound effects, music generation, and editing workflows.
- Build mechanisms to ensure character, scene, and narrative consistency across shots, episodes, and long-form productions.
- Collaborate with product, content, and AI teams to transform creative intent, storytelling structures, and cinematic language into scalable AI workflows.
Quality & Evaluation Systems
- Establish automated evaluation and quality-control frameworks covering generation quality, character consistency, scene continuity, subtitle alignment, and video production standards.
- Build monitoring, observability, and cost-optimization systems to improve platform reliability and operational efficiency.
- Define and track key metrics such as generation success rate, production quality, latency, cost per minute, and workflow efficiency.
Requirements
- Bachelor's degree or above in Computer Science, Software Engineering, or a related field.
- 3+ years of experience in Backend Engineering, Platform Engineering, AI Engineering, or related areas.
- Hands-on experience building and operating production AI Agent systems, LLM applications, Copilot products, or autonomous workflows.
- Strong understanding of modern Agent architectures, including:Function Calling;Tool Use;ReAct;Plan-and-Execute;Multi-Agent Collaboration;Context Management;Memory Management
- Experience with at least one modern Agent framework:LangGraph;AutoGen;CrewAI;Dify;OpenAI Agents SDK
- Strong background in distributed systems, high-concurrency services, and production platform architecture.
- Proficient in Python; experience with Go or Java is a plus.
- Experience with workflow orchestration systems such as:Temporal;Ray;Celery;Airflow;Custom workflow engines
- Ability to independently drive complex projects from system design through production deployment.
Domain Knowledge
- Familiarity with modern multimodal AI and video generation technologies, including text-to-video, image-to-video, reference-based generation, camera motion control, and character consistency workflows.
- Understanding of video production, storytelling, storyboards, cinematic language, or content creation pipelines.
Preferred Qualifications
- Experience launching AI Agent, Copilot, Autonomous Agent, or AI Workflow products from 0-to-1.
- Experience with AI video, AI short-drama, AI animation, or AI content-generation products.
- Familiarity with leading video-generation models such as Veo, Sora, Kling, Wan, Seedance, Vidu, MiniMax, or equivalent systems.
- Experience building Model Routing systems, Evaluation Pipelines, Prompt Optimization systems, or Multi-Agent architectures.
- Familiarity with MCP (Model Context Protocol), developer platforms, and AI tooling ecosystems.
- Experience with ComfyUI, FFmpeg, multimodal evaluation systems, or AI content-production workflows.
- Knowledge of voice cloning, lip-syncing, TTS systems, music generation, or audio production pipelines.
- Background in film, animation, advertising, content creation, or short-form video production.
- Experience building global consumer products and working in English-speaking environments.
- Previous experience as a Founding Engineer or an early‑stage startup technical leader.