Senior AI Engineer | Python, RAG, Voice AI, AWS, n8n, LangChain & Production LLM Systems

## Project Overview We are seeking a highly experienced **Senior AI Automation Engineer** to design and build production-grade AI applications that combine Large Language Models (LLMs), intelligent automation, cloud infrastructure, and scalable backend systems. This is **not** a basic chatbot project. We are looking for someone who can architect complete AI solutions—from backend APIs and retrieval systems to workflow automation and cloud deployment. The ideal candidate has hands-on experience building production AI systems using Python, AWS, modern LLM frameworks, and automation platforms. --- ## Responsibilities * Design and develop production-ready AI applications using Python. * Build intelligent AI agents capable of tool calling, memory, and multi-step reasoning. * Develop Retrieval-Augmented Generation (RAG) systems using vector databases and knowledge bases. * Engineer reliable prompts, structured outputs, and guardrails to ensure safe, accurate AI responses. * Integrate OpenAI, Claude, Gemini, or other LLM providers. * Create scalable REST APIs using FastAPI or Django. * Build workflow automations using n8n, Zapier, or Make. * Deploy applications on AWS using Docker and CI/CD best practices. * Integrate third-party services such as CRM platforms, Google Workspace, Microsoft Graph, Slack, Calendly, Stripe, and webhooks. * Design AI systems that interact with databases, external APIs, and internal business tools. * Optimize performance, security, monitoring, and deployment pipelines. * Write clean, maintainable, and well-documented production code. --- ## Required Skills ### AI & LLM Engineering * OpenAI GPT-4o * Claude * Gemini * Llama * Prompt Engineering * Function Calling * Structured Outputs * Multi-Agent Systems * AI Agent Architecture * Model Context Protocol (MCP) ### RAG & Knowledge Systems * LangChain * LangGraph * LlamaIndex * Pinecone * Weaviate * ChromaDB * Supabase Vector * Embedding Pipelines * Semantic Search * Knowledge Base Construction * Hallucination Reduction Techniques ### Backend Development * Python * FastAPI * Django * Flask * REST APIs * Async Programming * WebSockets * Celery * Redis ### Automation * n8n * Zapier * Make.com * Workflow Automation * AI Process Automation * CRM Automation * Webhooks ### Voice AI (Preferred) * Vapi * ElevenLabs * Retell AI * Twilio * LiveKit * Speech-to-Text * Text-to-Speech ### Cloud & DevOps * AWS EC2 * AWS Lambda * API Gateway * S3 * IAM * CloudWatch * Docker * Docker Compose * GitHub Actions * CI/CD * Linux ### Databases * PostgreSQL * MySQL * MongoDB * Redis * Supabase --- ## Nice to Have * AI-powered document processing * OCR pipelines * Computer Vision * AI Voice Agents * Healthcare AI * Recruitment Automation * AI Customer Support * Internal Enterprise AI Assistants * Agentic Workflows * Prompt Evaluation and Testing * AI Observability and Monitoring --- ## What We're Looking For We're looking for an engineer who understands how to build **real AI products**, not just prototype chatbots. You should be comfortable designing scalable architectures, integrating multiple AI services, orchestrating automation workflows, deploying to AWS, and delivering reliable, production-ready applications. If you've built AI agents, RAG systems, workflow automation, voice AI applications, or cloud-native AI platforms, we'd love to hear from you. When applying, please include: * Relevant AI projects you've built. * GitHub or portfolio links. * Technologies used. * Your role in the project. * Experience with AWS deployments. * Experience with n8n or workflow automation. * Experience building RAG or multi-agent systems. * Examples of production AI applications you've delivered. We value engineers who can own projects end-to-end—from architecture and implementation to deployment and optimization. ~Mathew Please include keywork "Flab" at the start of your proposal to get noitced