AI Engineer for Custom Persona & Agentic RAG

About the Role: We are looking for an experienced AI/LLM Engineer to design, build, and deploy an AI persona bot ("Digital Twin") that accurately replicates the knowledge base, communication style, reasoning patterns, and decision-making approach of a founder/executive. Key Responsibilities: Data Ingestion Pipeline: Clean, format, and vectorize a dataset of personal writings, audio transcripts, emails, and documentation into a structured vector database. Agent Architecture: Implement an Agentic RAG pipeline using frameworks such as LangChain, LlamaIndex, or AutoGen. System Prompting & Fine-Tuning: Design robust system instructions and few-shot prompt banks to mirror voice, tone, and specific behavioral guidelines. Deployment: Deploy the solution on Google Cloud Platform (Vertex AI, Cloud Run) or an equivalent cloud infrastructure with secure API endpoints. Integrations: Connect the agent to front-end communication channels (e.g., Slack, Web Chat, WhatsApp, or Email). Required Skills & Qualifications: Strong experience building LLM-backed applications, custom AI personas, and RAG architectures. Proficiency with Python and AI frameworks (LangChain / LlamaIndex / LangGraph). Hands-on experience with GCP (Vertex AI Search & Conversation, Vector Search, Cloud Run). Experience with vector stores (Pinecone, ChromaDB, or Vertex AI Vector Search) and memory systems (Mem0, Zep). Knowledge of guardrails and safety controls to prevent prompt injection and hallucinations. Preferred Experience: Prior experience creating AI persona bots, executive assistants, or voice/digital clones.