AI Architect - Production LLM Systems (Azure)

Responsibilities

• Define and evolve the AI architecture roadmap for Oscar, building scalable patterns for LLM integration, RAG pipelines, and agent-based workflows
• Architect and optimize production-grade RAG systems, including retrieval strategies, embedding design, vector search tuning, and model orchestration in Azure
• Lead technical spikes and convert prototypes into secure, production-ready implementations
• Establish observability, alerting, cost efficiency, and performance standards for AI services operating at enterprise scale
• Mentor engineers through Sprint execution, conduct design and code reviews, and elevate overall engineering quality
• Evaluate emerging AI frameworks (e.g., MCP, orchestration patterns) and introduce practical innovations aligned to product roadmap needs

Requirements

• Bachelor's Degree plus at least 10 years of distributed systems or enterprise platforms experience, including 3+ years deploying AI/LLM systems into production environments, or demonstrated equivalent experience and education
• Proven hands-on experience designing and implementing RAG architectures in enterprise environments
• Deep expertise with Azure cloud services and cloud-native application design
• Strong foundation in APIs, distributed systems, security controls, and production observability
• Comfortable operating hands-on while leading technical direction
• Experience building or scaling enterprise chatbots or AI-driven internal platforms
• Familiarity with agent orchestration frameworks, Model Context Protocol (MCP), MLOps/DevSecOps practices, and multi-agent architectures
• Relocation assistance is not available for this position
• Sponsorship for US work authorization is not available for this position, now or in the future.
• About AECOM
• What makes AECOM a great place to work
• As an Equal Opportunity Employer, we believe in your potential and are here to help you achieve it. All your information will be kept confidential according to EEO guidelines.

Benefits

Additional Information

As an AI Architect, you will lead the architectural evolution of Oscar, our enterprise AI platform used across the organization. This is a highly technical, hands-on role focused on building secure, observable, production-grade LLM systems at scale. You will define the architectural runway for future capabilities like agent orchestration, tool-use frameworks, and enterprise data integration while staying deeply engaged in technical spikes, design reviews, and delivery execution. This role sits at the intersection of LLM engineering, Azure cloud architecture, and real-world enterprise deployment. This position will offer flexibility for hybrid work schedules to include both in-office presence and telecommute/virtual work, to be based from either Houston or Dallas, TX.

Your Match

How well this role fits your profile.

Company Intel

What employees say

Worked at Aecom2? Share your experience