Agentic AI Engineer

Join us to build cutting-edge AI agent workflows that automate the entire media lifecycle—from content creation to publishing. You'll design autonomous systems using tools like n8n, LangChain, and ComfyUI to scale image, video, and voice content with minimal human input. What You'll Do Design and build autonomous agent workflows for media automation using tools like n8n, LangChain, and Autogen. Develop pipelines that create, schedule, and deploy images, videos, voiceovers, and social posts—end-to-end, powered by AI agents. Integrate with external APIs (Google Drive, Notion, YouTube, Instagram, ElevenLabs, RunPod, etc.) to turn agent decisions into real-world actions. Build multi-agent systems that collaborate: for example, one agent creates content, another schedules it, another handles QA. Use LLMs (OpenAI, Claude, Llama, Mixtral) with memory and reasoning to automate multi-step creative and analytical tasks. Own and optimize n8n workflows with dynamic inputs, conditional branches, webhook triggers, and external tool execution. Write clean orchestration logic in Python where needed to complement n8n's visual workflows. Package your systems in Docker or serverless deployments and document for reproducibility. Must-Have Skills Strong Python foundation, including REST APIs and async logic. Experience with Gen AI tools: image (SD, ComfyUI), text (LLMs), voice (TTS/ASR). Understanding of agentic AI frameworks like LangChain, Autogen, CrewAI. Ability to turn prompts + APIs into scalable workflows that produce real results. Nice to Have Experience with media automation pipelines: text-to-image, image-to-video, text-to-voice, etc. Familiarity with ComfyUI, ElevenLabs, RunPod, or Stable Video Diffusion. Knowledge of vector stores (FAISS, Supabase, Pinecone) for memory. Portfolio showing an end-to-end AI automation system or multi-agent workflow. Awareness of content scaling problems: how to go from 1 post → 1000 assets with minimal human input.