Tech Lead AI Engineer

• Agentic AI - Customer & Commercial Pod
  In the Agentic AI – Customer & Commercial Pod, you’ll lead the development of intelligent, Customer‑facing AI agents that simplify how Customers get help, explore options, and complete transactions. This role operates at the intersection of advanced agentic AI and robust software engineering—translating use cases into scalable, reusable agent capabilities that Teams across Southwest can trust and extend. You’ll set technical direction for agentic systems, lead architecture and design reviews, and guide teams building task‑oriented agents with planning, tool orchestration, fallbacks, and safety controls. With strong ownership of evaluation strategies, observability, and reliability practices, you’ll ensure non‑deterministic systems are safe, performant, and production‑ready. Leveraging AWS‑first implementations, including Bedrock agents and secure cloud patterns, you’ll help shape AI experiences that evolve over time while maintaining enterprise‑grade standards and Customer trust.

• Agentic AI - ETO Support Pod
  In the Agentic AI – ETO Support Pod, you’ll lead the delivery of agentic AI systems that support enterprise and back‑office Technology Teams by simplifying complex internal workflows and improving operational efficiency. This pod focuses on building production AI frameworks, orchestration patterns, and evaluation standards that scale across the organization. As a Tech Lead, you’ll own end‑to‑end architecture and delivery for agentic systems—spanning model integration, RAG architectures, orchestration frameworks, and production operations. You’ll define standards for agent design, evaluation, and reliability while guiding teams through complex technical problem‑solving in real enterprise environments. Working extensively with Python‑based AI systems, AWS services such as Bedrock and SageMaker, and modern CI/CD and observability tooling, you’ll help establish foundational AI capabilities that other teams rely on to deliver secure, performant, and maintainable solutions at scale.

• Lead and motivate team in building and operating task-oriented agents (planner/executor, tool routing, HITL checkpoints, fallbacks, circuit breakers) with clear interfaces and SLOs.
• Provide technical direction for design and productionization of retrieval/grounding pipelines (RAG, structured APIs, metadata/knowledge graphs), including chunking, summarization, embeddings lifecycle, and relevance tuning.
• Create, maintain, and review prompt engineering strategies including modular system/instruction prompts and tool specs; guide versioned prompt libraries, A/B variants, and promotion criteria.
• Plan and oversee evaluation frameworks including per-use-case eval suites (functional, behavioral, safety, latency, cost); guide automation of offline/online evals and eval gates into CI/CD pipelines.
• Provide oversight for security and compliance strategies including PII redaction, policy-as-code checks, guardrails, and compliant audit trails across agents and context pipelines.
• Identify and resolve optimization challenges for strategies for context size, caching, rerankers, model selection, and tool routing to reduce cost per successful task.
• Act as technical interface for data engineering architecture including schemas/data contracts, batch/stream ETL for context stores, embedding jobs, and freshness SLAs (with Data Platform).
• Investigate and approve integration strategies with runtime frameworks (e.g., LangGraph/AgentCore, Bedrock Agents/Guardrails) and enterprise systems.
• Evaluate and ensure documentation standards including agent cards, runbooks, and playbooks; guide 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

• Expert knowledge of embeddings, retrievers, and vector DBs (e.g. pgvector, OpenSearch k-NN); relevance tuning and evals.
• Expert knowledge of LLMs and agentic infrastructure such as LangGraph, AWS Bedrock (Agents/Guardrails) or other agentic frameworks.
• Expert knowledge of the full AWS stack (Bedrock, SageMaker, Lambda, S3, Redshift, VPC) and enterprise data platforms
• Ability to advise on translating user journeys into measurable agent behaviors; guide creation of clear design docs and runbooks.
• Expert experience implementing AI observability tooling for tracing and evaluation.
• Ability to advise on 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 advising cross-functional leaders.
• Skilled in Git-based workflows, automated tests (unit/integration/eval).

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

Experience

• Required: Expert level experience, expansive and far reaching knowledge in:

  • Applied artificial intelligence engineering, including the design, development, deployment, and operation of AI‑enabled systems

  • 8-10 years of relevant work-related experience

  • Sets technical direction for agentic systems; leads design reviews and guides teams building production AI capabilities.

  • Architects task-oriented agents (planner/executor, tool routing, fallbacks/circuit breakers) and ensures safe scaling to production.

  • Owns evaluation strategy + reliability practices (observability, SLOs, incident readiness) for non-deterministic systems.

  • Strong AWS-first implementation (Bedrock Agents/Guardrails or similar) with secure IAM/network patterns and enterprise integration expertise.

  • Mentors engineers and communicates options/risks/impact to leadership; drives “shift-left” quality practices.

• Preferred: Experience in:

  • Deep LLMOps/MLOps experience (datasets, evaluation pipelines, drift monitoring).

  • Cost/latency optimization and FinOps practices for GenAI workloads.

  • Experience leading cross-team architecture alignment and setting shared standards.

  • Multi-agent architectures in production (orchestration, tool use, safety constraints).

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