Principal AI Engineer

The Principal AI Engineer will be an early member of a greenfield AI engineering organization focused on delivering innovative AI solutions that improve advisor productivity, automate workflows, reduce administrative overhead, and enhance client experiences. This hands‑on role will shape technical direction, establish engineering best practices, and architect and deliver secure, scalable, enterprise‑grade AI capabilities from concept through production. The role sits at the intersection of Generative AI, data engineering, cloud architecture, and product innovation, requiring the ability to identify high‑value business problems and translate emerging AI capabilities into practical solutions with measurable business outcomes.

Key Responsibilities

• Design and deliver scalable, production‑grade AI applications and distributed systems.
• Develop AI‑powered solutions using large language models (LLMs), agent frameworks, and orchestration platforms.
• Design and implement Retrieval‑Augmented Generation (RAG), semantic search, and enterprise knowledge systems using vector databases and retrieval frameworks.
• Build AI‑powered capabilities for meeting preparation, research, call summarization, insight generation, workflow orchestration, knowledge retrieval, recommendations, decision support, and productivity enhancement.
• Develop workflow automation solutions leveraging enterprise data sources and communication channels.
• Collaborate with business leaders, product teams, architects, data scientists, engineers, and other stakeholders to identify high‑value AI use cases.
• Translate business problems and requirements into secure, scalable, and practical AI solutions.
• Architect and build complex AI solutions from concept through production deployment.
• Establish and influence engineering best practices, technical standards, and architectural direction for AI solutions.
• Deploy and scale AI applications across cloud environments.
• Apply modern platform engineering and DevOps practices, including containers, Kubernetes, Infrastructure-as-Code, and cloud‑native architectures.
• Ensure enterprise AI solutions meet security, reliability, scalability, and performance requirements.
• Drive initiatives across engineering, data, product, and business teams from concept to production.
• Evaluate emerging AI technologies and identify opportunities to apply them to business challenges.
• Deliver AI solutions that improve productivity, automate operational workflows, and create measurable business value.

Required Qualifications

• Bachelor's degree or equivalent experience with 8+ years of software engineering experience, or a Master's degree with 6+ years of software engineering experience.
• Proven experience designing and delivering scalable, production‑grade software solutions and distributed systems.
• Deep expertise building AI‑powered applications using large language models (LLMs), agent frameworks, and orchestration platforms such as OpenAI, Claude, Bedrock, LangChain, and LangGraph.
• Hands‑on experience developing Retrieval‑Augmented Generation (RAG) solutions, semantic search capabilities, and enterprise knowledge systems.
• Experience working with vector databases and retrieval frameworks.