Job Title: Full Stack Python Developer - W2 Role
Location: Dallas, TX (locals only)
in-person interview - Looking for only local candidate
Note/Comments: Interviews will have 2 rounds Top 3 . Candidate needs to complete the berribot AI interview today or tomorrow.
Candidate need to attend the in-person interview at client location. Looking for only local candidate . contracting profiles will be accepted only W2. No C2C profiles for this position.
Job description:
As a Software Engineer on the Agentic System Layer (ASL) team, you will build and maintain the core platform components that power American Airlines’ agentic AI systems. Day-to-day responsibilities include: developing and maintaining agent orchestration services, tool registries, and execution runtimes; building APIs and microservices for LLM integration, prompt management, and agent lifecycle management; implementing observability, logging, and monitoring for agentic workflows; writing comprehensive tests (unit, integration, end-to-end) for platform reliability; collaborating with architects on design decisions and with ML engineers on model integration; participating in on-call rotations for production support of the AI platform; contributing to CI/CD pipelines, infrastructure-as-code, and deployment automation.
Top 3 Mandatory Skills and Experience:
1) 5+ years software engineering experience with strong proficiency in Python, plus working knowledge of at least one of Java, Go, or TypeScript; hands-on experience building production REST/gRPC APIs and microservices.
2) Solid experience with cloud platforms (AWS or Azure preferred), containerization (Docker/Kubernetes), CI/CD pipelines, and infrastructure-as-code (Terraform, CloudFormation, or Pulumi).
3) Working experience with LLM integration patterns, prompt engineering, or AI/ML application development; familiarity with frameworks like LangChain, LangGraph, or similar orchestration tools.
Nice to Have Skills:
Experience with event-driven architectures (Kafka, EventBridge), vector databases, observability tools (Datadog, Splunk, OpenTelemetry), agent evaluation frameworks, FastAPI/Flask, async Python, Redis/caching patterns, airline or travel industry experience.
What Makes a Great Candidate?:
A great candidate is a solid mid-level to senior engineer who writes clean, testable code and has genuine curiosity about AI/ML systems. They do not need to be a deep ML expert, but they should understand how LLMs work, what agentic patterns look like, and how to build reliable services around non-deterministic components. They take ownership, write good tests, communicate clearly in code reviews, and are comfortable operating production systems.
Never miss an opportunity! Create an alert based on the job you applied for.
