AI Engineer III

FedEx; Plano (TX); Hybrid; USD 123,000 - 166,000; Full time

Job summary

FedEx is seeking an AI Engineer III in a hybrid role based in Plano, TX (also Memphis, TN or Pittsburgh, PA) to design, develop, deploy, and maintain governed AI/ML solutions for intelligent automation and analytics. You will work across multi-agent systems, RAG pipelines, and LLMOps, on Vertex AI and GCP.

You will collaborate with Data Scientists, Data Engineers, and Platform teams to move models from prototype to production, while ensuring observability, SLOs, and incident response readiness.

Qualifications

• Bachelor's degree in Computer Science, Data Science, Engineering, or related field is required.
• 3-5+ years of dedicated experience designing and shipping ML models to production.
• Experience leading the design of a significant ML-powered feature.

Responsibilities

• Design, develop, and maintain multi-agent systems and deterministic workflow agents.
• Deploy and operate ADK agents and tool integrations on Vertex AI and GCP.
• Create scalable ingestion, embedding, and RAG pipelines in Python.
• Implement HITL tool confirmations and session/state memory management.
• Ensure observability with tracing, logging, and performance monitoring.
• Collaborate with Data Scientists and ML/Ops to move models from prototype to production.
• Define and own SLOs, latency targets, and incident response strategies.

Skills

Multi-agent systems

Human-in-the-loop

Observability

ML production readiness

Education

Bachelor's degree in CS/DS/Engineering

Master's preferred

Tools

Python

Vertex AI

BigQuery Vector Search

GCS

Cloud Run

GKE

APIs

MCP (Model Context Protocol)

Job description

Advance production AI with FedEx as an AI Engineer III in a hybrid role based in Plano, TX (also available in Memphis, TN or Pittsburgh, PA). You will design, develop, deploy, and maintain governed AI/ML solutions for intelligent automation, predictive insight, and advanced analytics, working across multi-agent systems, RAG pipelines, LLMOps, observability, and operational readiness on GCP.

What you'll do

• Design, develop, and maintain multi-agent systems, including deterministic workflow agents and autonomous tool-calling pipelines using Google Agent Development Kit (ADK) in Python.
• Use the Google Agent CLI (agents-cli / adk) to scaffold, run, test, evaluate, and package agent projects across development, staging, and production.
• Implement complex agentic patterns such as graph-based workflow runtimes, hierarchical multi-agent delegation, human-in-the-loop (HITL) tool confirmations, and session/state memory management.
• Build custom agent tools and integrate Model Context Protocol (MCP) tools and API connectors powered by foundation models on Vertex AI.
• Design high-performance RAG architectures integrated with ADK using Vertex AI Vector Search, BigQuery Vector Search, and Cloud Storage (GCS).
• Build scalable ingestion, chunking, and embedding pipelines with Python, Cloud Dataflow (Apache Beam), and Cloud Run Jobs.
• Integrate enterprise datastores (such as BigQuery, Cloud SQL / AlloyDB pgvector, and Firestore) as tool-accessible datastores for autonomous agents.
• Deploy and operationalize ADK agents to Vertex AI Agent Engine (Reasoning Engines), Cloud Run, and GKE using the Agent CLI and containerized Python runtimes.
• Create automated evaluation suites using agents-cli eval, Vertex AI GenAI Evaluation Service, and continuous regression testing for reasoning, tool fidelity, and context relevance.
• Implement production-grade observability with session telemetry, step-by-step tracing, and latency monitoring using Cloud Trace, Cloud Logging, and Vertex AI Model Monitoring.
• Define and own Service Level Objectives (SLOs) including TTFT, p50/p95 execution latency, tool invocation error rates, and agent task completion rates.
• Secure agent tool execution and data mutations using least-privilege IAM, VPC Service Controls, Secret Manager, and zero-trust safety guardrails.
• Expose agent capabilities via asynchronous FastAPI / gRPC microservices and register deployed agents into enterprise portals.
• Stay current with advancements in the Google agent ecosystem, including new ADK features, multimodal agents, and reasoning paradigms.
• Work closely with Data Scientists, Data Engineers, ML Ops Engineers, and Platform teams to move models from prototype to production.
• Own end-to-end operational readiness for AI use cases by establishing observability, SLOs, and incident response and rollback strategies.

Requirements

• Bachelor's degree in Computer Science, Data Science, Engineering, or related field is required; Master's preferred.
• 3-5+ years of dedicated experience designing and shipping ML models to production.
• Experience leading the design of a significant ML-powered feature.

Technologies you'll work with

• Google Agent Development Kit (ADK), Python, Google Agent CLI (agents-cli / adk)
• Vertex AI, Vertex AI Vector Search, BigQuery Vector Search, GCS
• Cloud Dataflow (Apache Beam), Cloud Run Jobs, BigQuery, Cloud SQL, AlloyDB pgvector, Firestore
• Vertex AI Agent Engine (Reasoning Engines), Cloud Run, GKE, Model Context Protocol (MCP)
• agents-cli eval, Vertex AI GenAI Evaluation Service, Cloud Trace, Cloud Logging, Vertex AI Model Monitoring
• FastAPI, gRPC, OpenAPI, asyncio, Cloud Build, Docker, Artifact Registry
• Vertex AI Studio / Model Garden, Vertex AI Endpoints
• Least-privilege IAM, VPC Service Controls, Secret Manager, Cloud Firestore

Hybrid location and on-site expectations

• This is a hybrid position in Plano, TX (first preference), Memphis, TN, or Pittsburgh, PA.
• Candidates residing within 50 miles of a FedEx campus will be required to work on-site at a FedEx location several times per week.

Pay transparency

• Plano, TX / Pittsburgh, PA: $122,778 to $165,750 per year
• Memphis, TN: $116,639 to $157,463 per year

Comprehensive benefits: For details on FedEx's benefits, click here.

Applicants have rights under federal employment laws: Know Your Rights, Pay Transparency, Family and Medical Leave Act (FMLA), Employee Polygraph Protection Act.

E-Verify program participant: Federal Express Corporation participates in the U.S. Department of Homeland Security E-Verify program. E-Verify Notice (bilingual) and Right to Work Notice (English / Spanish).