Job Description

Department:

Technology

Our Company Promise

We are committed to provide our Employees a stable work environment with equal opportunity for learning and personal growth. Creativity and innovation are encouraged for improving the effectiveness of Southwest Airlines. Above all, Employees will be provided the same concern, respect, and caring attitude within the organization that they are expected to share externally with every Southwest Customer.

As a Sr AI Engineer Global supporting Southwest’s Agentic AI initiatives, you’ll build and operate production‑ready AI services that are reliable, secure, and scalable. This role is hands‑on and engineering‑driven—developing backend services and APIs, integrating event streams and data stores, and delivering AI capabilities through AWS‑native patterns. You’ll contribute across the full lifecycle: implementing solutions, automating deployments with IaC and CI/CD, instrumenting observability (logs, metrics, dashboards), and improving operational readiness through strong debugging and testing practices. You’ll work closely with Product, Platform, and Security partners to deliver AI systems that meet enterprise standards and create measurable impact for Southwest Teams and Customers. As we continue to grow our Global Innovation Center (GIC) in Hyderabad, we’re hiring multiple Sr AI Engineers across a variety of Pods and initiatives—each offering the opportunity to lead meaningful work, navigate complexity, and help advance the technology that powers Southwest’s operation. Read on to learn more about the Pods you could support.

• Agentic AI - Customer & Commercial
  In the Agentic AI – Customer & Commercial Pod, you’ll help build intelligent, Customer‑facing AI experiences that make it easier to get help, explore options, and complete transactions through simple, plain‑language interactions. In this role, you’ll implement scalable AI systems end‑to‑end—spanning model orchestration, deployment, monitoring, and reliability on an enterprise AI platform. You’ll bring strong retrieval and grounding expertise (RAG plus structured context), including embeddings lifecycle, freshness expectations, reranking, and relevance evaluation, to ensure responses are accurate and useful. You’ll also help define quality bars by wiring evaluation gates into CI/CD, monitoring drift and regressions, and improving performance over time. With a focus on production outcomes, you’ll optimize latency and cost per successful task while meeting SLOs, and apply enterprise controls such as PII handling, policy‑as‑code, safety guardrails, and auditability—helping Teams deliver AI capabilities that Customers can trust.

• Agentic AI - ETO Products
  In the Agentic AI – ETO Products Pod, you’ll build agentic AI solutions that support enterprise and back‑office technology teams by simplifying internal workflows and improving operational efficiency. You’ll ship production agentic systems using frameworks such as LangGraph, CrewAI, Bedrock, and RAG, applying practical engineering tradeoffs to solve real enterprise problems. This role is ideal for Engineers who enjoy building full solutions—not just prototypes—by delivering production Python services (FastAPI, async patterns, testing, packaging), integrating with AWS services, and ensuring reliability through observability and operational readiness. You’ll also help influence the frameworks, orchestration patterns, and evaluation standards that other Teams will adopt over time, strengthening how Southwest develops and scales AI across the organization.

Responsibilities

• Drive the design and building and operation of task-oriented agents (planner/executor, tool routing, HITL checkpoints, fallbacks, circuit breakers) with clear interfaces and SLOs.
• Drive the design and productionization of retrieval/grounding pipelines (RAG, structured APIs, metadata/knowledge graphs), including chunking, summarization, embeddings lifecycle, and relevance tuning.
• Serve as technical SME for prompt engineering efforts including authoring modular system/instruction prompts and tool specs; drive versioned prompt libraries, A/B variants, and promotion criteria.
• Drive evaluation strategy by defining per-use-case eval suites (functional, behavioral, safety, latency, cost); drive automation of offline/online evals and eval gates into CI/CD pipelines.
• Drive implementation of PII redaction, policy-as-code checks, guardrails, and compliant audit trails across agents and context pipelines.
• Drive optimization efforts for context size, caching, rerankers, model selection, and tool routing to reduce cost per successful task.
• Serve as technical lead for data engineering efforts including schemas/data contracts, batch/stream ETL for context stores, embedding jobs, and freshness SLAs (with Data Platform).
• Drive integration efforts with runtime frameworks (e.g., LangGraph/AgentCore, Bedrock Agents/Guardrails) and enterprise systems.
• Drive documentation standards and mentor team on efforts including agent cards, runbooks, and playbooks; drive development of templates and internal libraries for repeatable delivery within the Southwest Airlines AI community.
• Mentor AI engineers through coaching and training.
• May perform other job duties as directed by Employee's Leaders

Knowledge, Skills and Abilities

• Advanced knowledge of embeddings, retrievers, and vector DBs (e.g. pgvector, OpenSearch k-NN); relevance tuning and evals.
• Advanced knowledge of LLMs and agentic infrastructure such as LangGraph, AWS Bedrock (Agents/Guardrails) or other agentic frameworks.
• Advanced knowledge of the full AWS stack (Bedrock, SageMaker, Lambda, S3, Redshift, VPC) and enterprise data platforms
• Ability to lead translation of user journeys into measurable agent behaviors; drive creation of clear design docs and runbooks.
• Advanced experience implementing AI observability tooling for tracing and evaluation.
• Ability to lead efforts balancing innovation with stability in mission-critical AI infrastructure.
• Skilled in agile methodologies and iterative delivery of complex systems.
• Strong conflict resolution, prioritization, and consensus-building skills for leading cross-functional teams.
• Skilled in Git-based workflows, automated tests (unit/integration/eval).

Education

• Required: Bachelor's Degree in Mathematics, Computer or Data Sciences, Information Technology or similar fields of study; or equivalent advance level experience

Experience

• Required: Advanced-level experience, seasoned and specialized knowledge in:
  • Applied artificial intelligence engineering, including the design, development, deployment, and operation of AI‑enabled systems
  • 5-7 years of relevant work-related experience
  • Advanced experience shipping AI/agentic capabilities end-to-end; translates journeys into measurable behaviors and production runbooks.
  • Deep retrieval/grounding expertise (RAG + structured context): embeddings lifecycle, freshness SLAs, rerankers, and relevance evaluation.
  • Defines quality bars and evaluation strategy; wires eval gates into CI/CD and monitors drift/regressions in production.
  • Optimizes latency and cost per successful task (context sizing, caching, model selection, tool routing) while meeting SLOs.
  • Enterprise controls: policy-as-code, PII handling, safety guardrails, and auditability; mentors engineers on eval-driven delivery.
• Preferred: Experience in:
  • Managing versioned prompt libraries and promotion criteria; experimentation (A/B/canary) for model/prompt changes.
  • Knowledge graphs/metadata strategies for grounding and retrieval tuning at scale.
  • Experience with compliance/audit patterns for AI systems and policy-as-code guardrails.
  • Experience coaching teams on eval-driven delivery and reliability for non-deterministic systems.

Other Qualifications

• Must meet confidentiality expectations as to confidential, proprietary and sensitive Company information
• Ability to work extended hours as needed

Southwest Airlines is an Equal Opportunity Employer.
Please print/save this job description because it won't be available after you apply.