Lead AI Engineer

We are looking for a Lead AI Engineer to design, develop, and deploy scalable Generative AI and conversational AI solutions for enterprise environments. This role leads the implementation of LLM-powered applications, RAG architectures, multi-agent workflows, and AI-driven APIs, ensuring high standards for security, reliability, and performance. The ideal candidate brings strong expertise in Python, GCP, enterprise chatbot development, and AI orchestration frameworks, along with experience evaluating, optimizing, and monitoring AI solutions. Working closely with product, engineering, and business stakeholders, the Lead AI Engineer drives the adoption of innovative AI technologies that deliver measurable business value.

This role is based on client site in Dallas, TX for 2-3 days per week

• Design, develop, and deploy scalable Generative AI and chatbot solutions for production environments, ensuring security, performance, and reliability.
• Build Python-based APIs and agentic workflows using Google ADK, FastAPI, LangGraph, Copilot Studio, or similar frameworks.
• Implement and optimize RAG (Retrieval-Augmented Generation) architectures, vector databases, and knowledge retrieval systems to improve chatbot accuracy and reduce hallucinations.
• Develop and maintain backend services that expose AI capabilities through secure, scalable APIs.
• Design agentic AI patterns such as supervisor/orchestrator, fan-in/fan-out, retrieval, research, and evaluation workflows.
• Establish observability, monitoring, and evaluation frameworks to measure chatbot performance, response quality, and business outcomes.
• Evaluate emerging AI models, tools, and platforms and recommend best practices for enterprise adoption.
• Collaborate with product, engineering, and business stakeholders in a spec-driven development environment.