Title: Principal AI Engineer – Agentic AI | Contract to Hire | Irvine, CA (Hybrid) | AS

Title: Principal AI Engineer - Agentic AI| Contract to Hire | Irvine, CA (Hybrid) | AS

Central Business Solutions, Inc(A Certified Minority Owned Organization)

Required Qualifications

• Bachelor's or Master's degree in Computer Science, Artificial Intelligence, Machine Learning, or related field.
• 12+ years of software engineering experience.
• 5+ years building AI/ML applications.

About the Role

We are seeking a Senior/Principal AI Engineer to design and build production-grade Agentic AI and Generative AI applications that enable Client's executives to interact with operational data through a conversational interface.

The ideal candidate will have strong experience building LLM-powered applications, AI agents, RAG solutions, tool-calling workflows, and data-grounded AI systems, with a strong focus on accuracy, trust, scalability, and production readiness.

Key Responsibilities

• Design and develop Agentic AI / LLM-based applications for enterprise use cases.
• Build conversational AI experiences that allow users to query complex operational data using natural language.
• Develop agent workflows using frameworks such as LangGraph and LangChain.
• Design single-agent and multi-agent architectures based on business and technical requirements.
• Build RAG and retrieval workflows using vector search, embeddings, and PostgreSQL/pgVector.
• Develop controlled tool-calling and SQL-based data retrieval workflows.
• Implement mechanisms to prevent hallucinations and ensure responses are grounded in authoritative data.
• Design validation processes for data availability, freshness, accuracy, and provenance before generating responses.
• Integrate AI agents with enterprise data sources and APIs.
• Work with AWS-based data and AI infrastructure.
• Evaluate and optimize LLM application performance, including latency, token usage, cost, and response quality.
• Design approaches for managing long conversational context, intent routing, and context isolation.
• Implement real-time status/progress updates for long-running AI workflows using technologies such as WebSockets or Server-Sent Events.
• Establish evaluation frameworks and metrics for AI accuracy, grounding, hallucination, and overall system quality.
• Collaborate with product managers, data engineers, architects, and business stakeholders.
• Lead technical discussions, architecture decisions, code reviews, and mentor other engineers.

Required Technical Skills

• Strong experience with Generative AI / LLM applications
• Hands-on experience with Agentic AI
• LangGraph and/or LangChain
• Python & AWS
• RAG / Retrieval-Augmented Generation
• Vector databases / Vector Search / Embeddings
• PostgreSQL
• SQL / Text-to-SQL
• Experience with LLM tool calling / function calling
• Understanding of multi-agent architectures and orchestration
• Strong understanding of prompt engineering and system prompts
• Experience addressing LLM hallucination, grounding, context management, and response accuracy
• Strong software engineering and system design experience