AI Engineer

Role Overview As the AI Engineer, you will be responsible for designing, building, deploying, and operating an internal multi-agent AI system that automates complex knowledge-based workflows. You will own the AI system end-to-end, from architecture and development through deployment, integration, monitoring, and continuous improvement. Working directly with leadership, you will translate business requirements into reliable AI solutions while ensuring appropriate governance, security, auditability, and human oversight. This is a build-and-own role for an engineer with experience taking AI applications into production who is comfortable owning complete systems rather than working only on isolated technical tasks. Key Responsibilities -AI Agent Development & System Architecture -Retrieval-Augmented Generation (RAG) & Knowledge Systems -Automation & Business System Integrations -Human Oversight, Security & Compliance -Cloud Infrastructure & Production Operations

Experience -Several years of professional software engineering experience. -Recent hands-on experience building and deploying LLM-based or agentic AI systems into production. -Experience owning technical systems from architecture and development through deployment and ongoing maintenance. -Demonstrated ability to independently design, build, and maintain production applications. Skills -Has strong Python programming experience and can use Python to develop production-ready AI applications and supporting systems. -Has hands-on experience with AI agent and workflow orchestration frameworks such as LangGraph, LangChain, or similar technologies. -Understands event-driven architectures and can apply them when designing scalable AI workflows and integrations. -Has strong experience working with LLM APIs, prompt engineering, tool calling, structured outputs, and AI evaluation methods. -Can build and consume REST APIs, webhooks, and third-party integrations to connect AI applications with existing business systems. -Has hands-on experience implementing Retrieval-Augmented Generation (RAG) systems using vector databases, embeddings, semantic retrieval, and retrieval quality evaluation. -Can monitor, troubleshoot, and debug AI applications operating in production environments. -Has experience deploying applications using AWS, GCP, or similar cloud infrastructure. -Understands CI/CD pipelines, containerization, secure data handling, and production monitoring practices. -Can design AI systems with appropriate human-in-the-loop controls, logging, auditability, security, and governance. -Can communicate complex technical concepts clearly to leadership and other non-technical stakeholders.