Principal AI Engineer

Location:

Irvine, CA, 92617

Lead the design and implementation of advanced AI solutions, primarily utilizing LLMs for natural‑language interaction with enterprise data. This Principal Engineer role involves designing and building production AI applications (including conversational agents and RAG systems) to turn business questions into actionable insights. Expertise in modern LLM framework, embeddings, chunkings, and enterprise integration patterns is required to deliver intelligent, scalable solutions. This client‑facing position necessitates communicating complex AI system behaviors to both technical and business leadership.

• Lead the end‑to‑end development of advanced AI solutions, including agentic systems, RAG pipelines, and multi‑agent workflows
• Design and implement embedding and chunking strategies essential for effective Retrieval‑Augmented Generation (RAG) across enterprise data
• Create integrations to connect AI agents with enterprise data systems, APIs, and services
• Develop robust, production‑grade asynchronous Python applications with proper error handling and session management
• Implement vector database and graph database solutions for semantic search and knowledge representation
• Establish agentic architecture, including data flows, interfaces, and mechanisms across all enterprise systems
• Deploy and manage AI agents on cloud platforms using CI/CD pipelines, infrastructure as code, and managed AI services
• Implement monitoring, logging, and observability for agent interactions to guarantee system reliability and support debugging
• Develop context engineering strategies that assemble dynamic context for consistent and accurate Large Language Model (LLM) behavior
• Engage with clients to translate business requirements into AI solution architectures, and balance feature development with technical debt management

• Experience with AI/ML agent orchestration frameworks such as Google ADK, Lang Chain, or similar tools
• Experience with multi‑agent architectures and workflow orchestration patterns
• Experience with LLM evaluation methodologies, including metrics design, hallucination detection, and A/B testing for prompt optimization
• Understanding of context engineering principles, including dynamic context assembly, tool result formatting, and conversation state management
• Experience with Snowflake or Big Query, including query optimization and connection management
• Experience managing data systems, including persistence selection, schema design, and read/write tradeoffs
• Familiarity with MLOps patterns and model deployment pipelines

• Bachelor's degree in Computer Science, Computer Engineering, Software Engineering, Electrical Engineering, or a related computational field

• 7 – 10 years in software development, including experience working in and leading technical teams

• 3+ years of hands‑on experience with LLMs, AI agents, or applied AI systems
• Expertise in Python development, async programming patterns, and modern web frameworks
• Proven experience developing RAG applications, including embedding strategies, chunking approaches, and retrieval optimization
• Hands‑on experience with vector databases and graph databases for semantic search and knowledge representation
• Experience with multiple LLM providers (Gemini, Claude, LLaMA) and understanding of cost vs. capability tradeoffs
• Experience with enterprise application integration, including defining integration architecture, data flows, and interface design
• Strong understanding of SOA, microservices, or similar architectural patterns
• Experience with CI/CD pipelines and infrastructure as code for deploying AI applications
• Demonstrated ability to communicate with client leadership and translate business requirements into technical solutions
• Experience with fine‑tuning or adapting foundation models for domain‑specific applications
• Experience balancing feature development with technical debt management to deliver business value while maintaining quality

Compensation:

Base Pay Range: $ – $

Actual placement within this range may vary based upon, but not limited to, relevant…