Application Architect (AI & Cloud) - Flex

Before you apply to a job, select your language preference from the options available at the top right of this page.

Explore your next opportunity at a Fortune Global 500 organization. Envision innovative possibilities, experience our rewarding culture, and work with talented teams that help you become better every day. We know what it takes to lead UPS into tomorrow—people with a unique combination of skill + passion. If you have the qualities and drive to lead yourself or teams, there are roles ready to cultivate your skills and take you to the next level.

Job Description:

We are seeking a highly skilled Application Architect to lead the end-to-end architecture and modernization of enterprise applications incorporating Generative AI, agentic AI, cloud-native technologies, and enterprise systems . The ideal candidate combines strong enterprise application architecture fundamentals with hands-on experience designing AI-powered solutions using technologies such as LangGraph, LangChain, GCP, RAG, MCP, and modern observability frameworks . This role requires the ability to determine where AI adds value and where deterministic workflows, APIs, rules, and traditional application patterns provide the better solution.

Key Responsibilities

- Own end-to-end application architecture across frontend, backend, AI/agent layers, orchestration, integrations, data, and cloud services.
- Define scalable, reusable architecture patterns supporting multiple business capabilities, personas, and workflows.
- Determine appropriate use of deterministic workflows, APIs, rules, AI agents, and hybrid approaches based on reliability, performance, explainability, cost, and maintainability.
- Architect stateful and long-running workflows , including session and context management, checkpoints, retries, idempotency, human-in-the-loop interactions, and recovery patterns.
- Design agentic solutions using LangGraph, LangChain, RAG, APIs, MCP, and other orchestration patterns .
- Define secure multi-persona architectures with appropriate authentication, authorization, entitlements, data-access boundaries, and service identities.
- Architect integrations with enterprise APIs, transactional and legacy systems, SaaS platforms, and data services using REST APIs, Apigee/API gateways, MCP, messaging, and event-driven patterns .
- Define application data, semantic retrieval, vector search, and knowledge architecture patterns using appropriate relational, graph, vector, and search technologies.
- Define non-functional requirements for scalability, availability, performance, resiliency, security, maintainability, recoverability, and cost efficiency .
- Design cloud-native architectures on Google Cloud Platform (GCP) using services such as Vertex AI, GKE, Cloud Run, AlloyDB, BigQuery, Pub/Sub, and Eventarc.
- Establish architecture patterns for AI observability, distributed tracing, evaluation, monitoring, Responsible AI, and operational readiness .
- Define reference architectures, engineering standards, architecture decision records (ADRs), and reusable patterns, and guide engineering teams through implementation.
- Evaluate architecture alternatives through prototypes and proof-of-concepts and clearly communicate technical trade-offs to engineering, product, security, platform, and business stakeholders.
- Guide CI/CD, Infrastructure as Code, containerization, DevSecOps, and production deployment patterns .

Required Qualifications

- Bachelor’s degree in Computer Science, Engineering, or a related technical field.
- 12+ years of experience designing and delivering enterprise applications, including significant experience in Application or Solution Architecture.
- Strong experience with distributed systems, APIs, microservices, event-driven architecture, data persistence, state management, and enterprise integration patterns .
- Hands-on experience designing solutions using Generative AI, LLMs, agentic AI, RAG, and tool-calling architectures .
- Experience with LangGraph and/or equivalent agent orchestration frameworks , including stateful workflow and multi-agent patterns.
- Experience architecting cloud-native solutions on GCP .
- Strong experience integrating applications with enterprise APIs, transactional systems, and legacy platforms.
- Experience with enterprise security patterns including identity, authentication, authorization, service identity, secrets management, and least privilege.
- Experience with production observability, distributed tracing, resiliency, performance engineering, and operational readiness.
- Ability to develop prototypes and reference implementations to validate architectural decisions.
- Strong communication and stakeholder-management skills with the ability to translate complex business requirements into scalable technical solutions.

Preferred Qualifications

- Master's degree in Computer Science, Artificial Intelligence, Data Engineering, or a related discipline.
- Experience with MCP, LangFuse, OpenTelemetry, Vertex AI, Gemini, OpenAI, or Anthropic ecosystems.
- Experience with semantic and knowledge technologies such as Stardog, Neo4j, RDF, OWL, or SPARQL .
- Experience with vector search, embeddings, semantic retrieval, and enterprise knowledge platforms.
- Knowledge of Responsible AI, AI governance, LLMOps, and MLOps .
- Experience designing reusable enterprise AI capabilities or supporting large-scale application modernization.
- Relevant cloud, AI, security, or architecture certifications.

Technical Skills

- Architecture: Distributed systems, microservices, REST APIs, event-driven architecture, stateful workflows, integration patterns
- AI & Agentic: Generative AI, LLMs, LangGraph, LangChain, RAG, MCP, tool calling, multi-agent and human-in-the-loop patterns
- Cloud: GCP, Vertex AI, GKE, Cloud Run, BigQuery, AlloyDB, Pub/Sub, Eventarc
- Data & Knowledge: PostgreSQL, relational data modeling, vector search, semantic retrieval, knowledge graphs
- Security: IAM, RBAC/ABAC, OAuth/OIDC, service identity, secrets management
- Observability: LangFuse, OpenTelemetry, distributed tracing, AI/LLM evaluation and monitoring
- Engineering: Git, CI/CD, Terraform, DevSecOps, containerization, automated testing

Pay Range:

Our compensation reflects the cost of labor across several US geographic markets. The base pay for this position ranges from $128,172/year to 272,736/year. Pay is based on several factors including but not limited to, market location and may vary depending on job-related knowledge, skills, and education/training and a candidate’s work experience. Hired applicants may be eligible for annual short-term and/or long-term incentive compensation programs depending on the level of the position. Payments under these annual programs are not guaranteed and are dependent upon a variety of factors including, but not limited to, individual performance, business unit performance, and/or the company’s performance. Hired applicants may be eligible for Medical/prescription drug coverage, Dental coverage, Vision coverage, Flexible Spending Account, Health Savings Account, Dependent Care Flexible Spending Account, Basic and Supplemental Life Insurance & Accidental Death and Dismemberment, Disability Income Protection Plan, Employee Assistance Program, 401(k) retirement program, Vacation, Paid Holidays and Personal time, Paid Sick and Family and Medical Leave time as required by law, and Discounted Employee Stock Purchase Program.

Employee Type:
Permanent
UPS is committed to providing a workplace free of discrimination, harassment, and retaliation.

Employer will sponsor visas for specific positions. UPS is an equal opportunity employer. UPS does not discriminate on the basis of race/color/religion/sex/national origin/veteran/disability/age/sexual orientation/gender identity or any other characteristic protected by law.