Developer L3
About The Position
As a Software Engineer on the Agentic System Layer (ASL) team, you will build and maintain core platform components that power American Airlines’ agentic AI systems. The role involves developing agent orchestration services, tool registries, and execution runtimes; building APIs and microservices for LLM integration, prompt management, and agent lifecycle management; and implementing observability, logging, and monitoring for agentic workflows. You will write unit, integration, and end-to-end tests to support platform reliability, collaborate with architects on design decisions and ML engineers on model integration, participate in production on-call rotations, and contribute to CI/CD pipelines, infrastructure-as-code, and deployment automation. The ideal candidate is a mid-level to senior engineer who writes clean, testable code and is curious about AI/ML systems. Deep ML expertise is not required, but the candidate should understand LLMs and agentic patterns and know how to build reliable services around non-deterministic components. They should take ownership, write strong tests, communicate clearly in code reviews, and be comfortable operating production systems.
Requirements
- 5+ years of software engineering experience with strong proficiency in Python and working knowledge of at least one of Java, Go, or TypeScript.
- Hands-on experience building production REST or gRPC APIs and microservices.
- Experience with AWS or Azure, containerization with Docker or Kubernetes, CI/CD pipelines, and infrastructure-as-code tools such as Terraform, CloudFormation, or Pulumi.
- Working experience with LLM integration patterns, prompt engineering, or AI/ML application development.
- Ability to write clean, testable code and strong tests, communicate clearly in code reviews, take ownership, and operate production systems.
- The posting also lists 3–5 years of experience and Python for Data Science as mandatory skills.
Nice To Haves
- Familiarity with LangChain, LangGraph, or similar orchestration tools.
- Experience with event-driven architectures such as Kafka or EventBridge.
- Experience with vector databases.
- Experience with observability tools such as Datadog, Splunk, or OpenTelemetry.
- Experience with agent evaluation frameworks.
- Experience with FastAPI or Flask.
- Experience with async Python.
- Experience with Redis or caching patterns.
- Airline or travel industry experience.
Responsibilities
- Develop and maintain agent orchestration services, tool registries, and execution runtimes.
- Build APIs and microservices for LLM integration, prompt management, and agent lifecycle management.
- Implement observability, logging, and monitoring for agentic workflows.
- Write unit, integration, and end-to-end tests for platform reliability.
- Collaborate with architects on design decisions and with ML engineers on model integration.
- Participate in on-call rotations for production support of the AI platform.
- Contribute to CI/CD pipelines, infrastructure-as-code, and deployment automation.
Benefits
- Medical benefits options
- Dental benefits options
- Disability insurance
- Paid time off, inclusive of sick leave
- Other paid and unpaid leave options
Stand Out From the Crowd
Upload your resume and get instant feedback on how well it matches this job.
What This Job Offers
Job Type
Full-time
Career Level
Mid Level
Education Level
No Education Listed
