AI Video Agent Engineer

Europe. Posted 5 months ago

The role

The engineer will design and implement a multi-agent video editing system. This involves building orchestration pipelines, integrating multimodal APIs, and optimizing model interactions to transform ideas into structured video content.

What you will do

Design and implement the architecture of a multi-agent video editing system
Define system prompts, behavioral rules, and structured instructions for agents
Develop and maintain complex orchestration pipelines in n8n
Design robust pipelines for handling video, image, text, and metadata
Integrate external and internal APIs for multimodal generation and processing
Tune and optimize model interactions primarily based on Gemini models
Design systems that support vector databases, RAG, and memory

Required qualifications

Strong experience building multi-agent systems
Experience with agent orchestration, communication, and context passing
Hands-on experience with n8n
Experience with Agent tool-calling and n8n MCP
Strong practical coding skills in Python and JavaScript
Ability to navigate API documentation and integrate multimodal tools
Strong sense of visual rhythm and composition
Creative intuition and storytelling awareness
Good taste in video structure and montage
Ability to evaluate AI-generated output by creative quality and narrative coherence

Nice to have

ComfyUI custom nodes
lightweight APIs (e.g., HuggingFace Spaces or inference endpoints)
FFmpeg
video processing pipelines
image processing workflows
Deep understanding of frameworks such as LangGraph and LangChain
Experience designing long-term memory systems for agents
Experience building agents with feedback loops such as self-reflection, self-critique, or strategy correction
Experience with tools for monitoring, debugging, and evaluating agent chains such as LangSmith, Arize Phoenix, or Promptfoo

About the company

toogeza is a Ukrainian recruiting company focused on hiring talents and building teams for tech startups worldwide.