Sr. AI Engineer

Sr. AI Engineer

Location: Plano, TX (Onsite from Day 1)

Long Term Role Overview: We are looking for an AI Engineer to design, build, and maintain Agentic AI orchestration pipelines, RAG (Retrieval Augmented Generation) systems, and GenAI powered automation within an enterprise operations platform. The ideal candidate should have strong experience building LLM powered agent workflows, vector based knowledge retrieval, and data processing pipelines with a solid foundation in traditional ML modeling and data analysis.

Key Responsibilities

• Agentic AI Pipeline Development: Build and extend a LangGraph based multi agent orchestration system.
• RAG / Knowledge Base Engineering: Maintain and enhance document ingestion (PDF, TXT, CSV, Markdown via pdfplumber/python docx), text chunking, vector embeddings, semantic similarity search for enterprise knowledge ingestion.
• GenAI / LLM Integration: Integrate with internal GenAI LLM endpoints for natural language understanding, summarization, and agent reasoning. Design and optimize prompts, system directives, and LLM output parsing for production reliability.
• MCP Tool Server Dispatch: Work with the Model Context Protocol (MCP) tool server that advertises, registers, and dispatches tool calls at runtime enabling agents to dynamically invoke diagnostic, remediation, and notification tools.
• Data Processing Pipelines: Build ETL and data transformation pipelines using Python (pandas, openpyxl) for structured/semi structured data. Preprocess and normalize data for model training and agent consumption.

Required Skills

• 5 Years in AI/ML engineering, data engineering, or applied AI roles with hands on LLM/GenAI application development.
• Python: Strong proficiency in Flask, pandas, data processing libraries (pdfplumber, python docx, openpyxl), and async/streaming patterns.
• LLM Agent Frameworks: Hands on experience with LangGraph, LangChain, or similar agent orchestration frameworks. Understanding of tool calling patterns, multi step reasoning, and state management.
• RAG Vector Databases: Experience building RAG pipelines end to end document ingestion, chunking strategies, embedding generation, vector storage (ChromaDB or similar: Pinecone, Weaviate, FAISS), and retrieval augmented prompt construction.
• Prompt Engineering: Ability to design robust system prompts, execution directives, and guardrails for production LLM applications.