Overseas Contractor

About the role

This is a hybrid role located in Fort Worth, TX. There may be in-person client interviews if shortlisted.

Responsibilities

• Define and drive the technical architecture for American Airlines' agentic AI platform
• Design and evolve the architecture for multi-agent orchestration systems, tool-use frameworks, and LLM integration pipelines
• Establish patterns for agent reliability, observability, and guardrails at production scale
• Lead technical design reviews and produce architecture decision records (ADRs)
• Collaborate with ML engineers and software engineers to ensure platform components are scalable, secure, and maintainable
• Evaluate and integrate emerging agentic AI frameworks (e.g., LangGraph, CrewAI, Semantic Kernel, AutoGen)
• Define API contracts, data flow patterns, and integration standards across the AI platform ecosystem
• Mentor engineers on best practices for building production-grade AI systems

Requirements

• 10+ years software architecture experience with at least 3 years designing AI/ML platform systems, including hands-on experience with LLM orchestration frameworks (LangChain, LangGraph, Semantic Kernel, or similar)
• Deep expertise in distributed systems design, microservices architecture, event-driven patterns, and API design (REST/gRPC), with strong proficiency in Python and at least one of Java/Go/TypeScript
• Production experience building and deploying agentic AI systems or LLM-powered applications at scale, including prompt engineering, tool-use patterns, RAG pipelines, and agent reliability/observability

Nice to Have

• Experience with Kubernetes/container orchestration, cloud platforms (AWS/Azure/GCP), MLOps/LLMOps tooling, vector databases (Pinecone, Weaviate, pgvector), knowledge graphs, airline/travel domain experience, TOGAF or similar architecture certification, experience with multi-agent system design patterns and agent evaluation/benchmarking frameworks

What Makes a Great Candidate?

A great candidate is a seasoned architect who has shipped production agentic AI systems - not just prototypes. They can whiteboard a multi-agent orchestration system, debate tradeoffs between different LLM routing strategies, and then jump into code to prove out a design. They understand that agentic systems at airline scale need bulletproof reliability, graceful degradation, and real observability. They have opinions backed by experience, they push back on bad ideas constructively, and they make the engineers around them better.

Team Environment and Structure

The AI Platforms Capabilities team builds and operates the Agentic System Layer (ASL), which is American Airlines' core platform for deploying agentic AI systems. The team operates in an agile environment with a focus on rapid iteration, production reliability, and close collaboration between architects, engineers, and ML engineers. The team works hybrid from the DFW office. The resource will be embedded directly into the ASL squad, working alongside full-time engineers and architects on platform development, feature delivery, and production support. They will participate in sprint ceremonies, code reviews, and architecture discussions.