AI Automation & AI Agent Engineer — n8n, Python, LLMs & API Integrations

AI Automation & AI Agent Engineer — n8n, Python, LLMs & API Integrations About the Role We are looking for an experienced AI Automation & AI Agent Engineer to design, build, and maintain production-ready AI-powered automation systems. The ideal candidate combines strong software engineering fundamentals with hands-on experience building LLM-powered applications, AI agents, workflow automations, and API integrations. You will work on real-world automation and AI systems where reliability, scalability, maintainability, and business impact are more important than simply connecting tools together. We are looking for someone who can take a problem from architecture to implementation to testing to deployment to optimization. What You'll Work On - Design and build AI-powered business automations using n8n - Develop reliable AI agents using LLMs such as OpenAI, Anthropic/Claude, or similar models - Build custom automation logic and backend services with Python - Integrate external platforms through REST APIs, webhooks, OAuth, and SDKs - Design agent workflows involving tool calling, structured outputs, memory, retrieval, and decision-making - Build and integrate RAG-based AI applications when required - Connect AI systems with CRMs, databases, SaaS platforms, internal tools, and business applications - Develop custom Python services when low-code automation alone is not sufficient - Implement validation, error handling, retries, logging, monitoring, and fallback mechanisms - Debug and optimize existing AI workflows and automations - Improve the reliability, latency, cost, and accuracy of AI-powered systems - Document architectures, workflows, integrations, and technical decisions Core Requirements You should have strong hands-on experience with: - n8n - Python - REST APIs - Webhooks - JSON - API authentication and OAuth - OpenAI API and/or Anthropic API - LLM application development - AI agents and agentic workflows - Workflow automation - Git and GitHub - Debugging and troubleshooting - Database integration Strongly Preferred Experience with some of the following is a major plus: - LangGraph - LangChain - RAG - Vector databases - PostgreSQL - Supabase - FastAPI - Docker - MCP - Function and tool calling - Structured outputs - CRM integrations - SaaS integrations - Cloud deployment - Background jobs and queues - AI observability and monitoring What We Are Looking For We are not looking for someone who only knows how to connect a few n8n nodes or write basic prompts. We need an engineer who understands how to build reliable AI systems in production. You should be comfortable asking questions, challenging technical assumptions when necessary, proposing better architectures, and finding solutions independently. The ability to understand a business problem and translate it into a robust technical solution is extremely important. Working Style We value: - Strong ownership - Clear and proactive communication - High-quality engineering - Attention to detail - Problem-solving ability - Ability to work independently - Good documentation - Fast learning - Pragmatic decision-making We prefer someone who can explain why they chose a particular architecture or technology, rather than simply implementing instructions. Application Requirements Please include the following in your proposal: 1. 2–3 examples of AI automation or AI agent systems you have actually built. 2. A short explanation of your role in each project and what you personally implemented. 3. The technologies and architecture used. 4. Your experience with n8n, Python, LLMs, and API integrations. 5. Your GitHub, portfolio, demo, or Loom video if available. 6. Your hourly rate and availability. 7. Your preferred working hours and time zone. Technical Question Please briefly explain how you would architect the following system: A customer sends a request → an AI agent analyzes the request → the agent decides which tool or API to use → the API action is executed → the result is validated → the information is stored in a database → the customer receives a response. Please explain how you would handle: - Invalid LLM outputs - API failures - Retries - Authentication - Data validation - Logging - Human approval for sensitive actions - Monitoring - Cost control We are particularly interested in seeing how you think, not just which tools you use. Engagement This project can start with a small initial scope to evaluate technical fit and execution quality. For the right engineer, there is potential for a long-term collaboration involving increasingly complex AI automation, agentic systems, integrations, and product development. If you are passionate about building practical AI systems that solve real business problems, we'd love to hear from you.