We are seeking a Staff Agentic AI Engineer to architect and deploy production-grade AI agents powered by large language models (LLMs). You will design and standardize agent frameworks using LangChain and LangGraph, develop scalable Retrieval-Augmented Generation (RAG) pipelines, and implement robust evaluation, observability, and safety practices to ensure high-performing, reliable systems.

In this Staff-level role, you will define architectural patterns and engineering standards for agent orchestration, monitoring, and reliability. You’ll translate complex requirements into secure, scalable AI platforms, build reusable frameworks that accelerate team delivery, and drive the long-term technical strategy for agentic systems across the organization.

Location
This is an onsite position reporting in office 3 days a week – Phoenix, AZ

Required Skills & Experience:

• Extensive experience designing and deploying LLM-powered systems, including scalable RAG architectures.
• Proven track record building production-grade agentic systems with LangChain and LangGraph.
• Strong expertise in AI safety, guardrails, hallucination mitigation, and evaluation methodologies.
• Experience architecting multi-step agent workflows, tool integrations, and memory systems for complex, stateful interactions.

Desired Skills & Experience:

• Experience designing multi-agent or autonomous agent architectures.
• Knowledge of fine-tuning, model adaptation, or model routing strategies for LLMs.
• Experience building real-time or streaming AI systems.
• Advanced degree (Master’s or PhD) in Computer Science, AI, or a related field.

Compensation:
Annual performance based bonus

You will receive the following benefits:

• Medical Insurance

• Dental Benefits
• Vision Benefits
• Paid Time Off (PTO)
• 401(k)

Applicants must be currently authorized to work in the US on a full-time basis now and in the future.