AI Video Agent Engineer

This is a fully remote position, open to applicants in Europe.

📋 Description

• Create and execute a multi-agent video editing system that encompasses video analysis, narrative generation, editing orchestration, and production/output synthesis.

• Establish system prompts, behavioral guidelines, and structured instructions for agents.

• Develop and sustain intricate n8n orchestration pipelines.

• Implement multi-agent workflows, tool-calling logic, dynamic routing between tools and models, as well as context passing among agents.

• Allow pipelines to choose suitable models, tools, and strategies based on task specifications.

• Design multimodal data pipelines for video, images, text prompts, and structured metadata.

• Integrate both external and internal APIs for image generation, video generation, speech synthesis, audio generation, and video processing.

• Assess APIs and select appropriate tools and models for each task.

• Tune and enhance Gemini-based model interactions, prompts, structured outputs, tool-calling workflows, and agent collaboration logic.

• Optimize pipelines for quality, reliability, and execution efficiency.

• Develop future-ready systems that support vector databases, retrieval-augmented generation, agent memory, and contextual reasoning.

• Construct a pipeline that converts ideas and references into analyzed content, coherent narratives, selected visual/audio elements, and high-quality structured video output.

⛳️ Requirements

• Significant experience in building multi-agent systems, including intent and sub-intent modeling, agent orchestration, agent communication and transport layers, summarization pipelines, and context passing between agents.

• Practical experience with n8n, agent tool-calling, and n8n MCP.

• Experience in designing complex automation pipelines.

• Strong coding skills with a vibe coding mindset.

• Primary programming languages: Python and JavaScript.

• Ability to swiftly navigate API documentation and integrate tools for image generation, video generation, speech synthesis, audio generation, and multimodal analysis.

• Knowledge of how and where to obtain optimal generation quality for each modality.

• Strong sense of visual rhythm and composition.

• Creative intuition and storytelling awareness.

• Good taste in video structure and montage.

• Capability to evaluate AI-generated output based on creative quality and narrative coherence, beyond mere metrics.

• Preferred experience with FFmpeg, video processing pipelines, and image processing workflows.

• Bonus experience with ComfyUI custom nodes and lightweight APIs such as HuggingFace Spaces or inference endpoints.

• Nice to have: in-depth understanding of LangGraph and LangChain.

• Nice to have: experience in designing long-term agent memory systems.

• Nice to have: experience in building self-reflection, self-critique, or strategy-correction feedback loops.

• Nice to have: experience with LangSmith, Arize Phoenix, or Promptfoo for monitoring, debugging, and evaluating agent chains and prompt behavior.

🏝️ Benefits

• No benefits, perks, or compensation extras are specified.

• Full-time employment.