Senior AI Automation Engineer

Prologis•San Francisco, CA

About The Position

The Senior AI Automation Engineer accelerates the delivery and adoption of practical AI solutions across Digital Experience Technology and adjacent operational teams. This role partners with stakeholders supporting public websites, authenticated portals, service operations, managed service providers, marketing technology, digital platforms, and vendor management to identify high-value opportunities and translate them into production capabilities. The engineer leads work from discovery and prototyping through deployment, adoption, measurement, and continuous improvement. By establishing reusable engineering patterns, governance practices, and enterprise AI assets, this role helps improve customer and employee experiences while reducing manual effort and operational constraints.

Requirements

6+ years of professional experience in software engineering, AI engineering, automation engineering, digital technology, data and analytics, or a related technical field.
Demonstrated experience designing, building, and deploying AI-powered applications, agents, copilots, or workflow automation solutions.
Experience applying generative AI, large language models, embeddings, vector databases, retrieval-augmented generation, prompt engineering, and agent workflows to business problems.
Programming experience with Python and Node.js for APIs, automations, AI applications, Model Context Protocol servers, agent-to-agent services, and integrations.
Experience integrating enterprise systems through APIs, JSON, webhooks, authentication, event-driven workflows, and secure data exchange.
Experience with Dataiku, Snowflake, AWS, or comparable enterprise data and AI platforms.
Experience with CI/CD, Infrastructure-as-Code, containers, DevOps practices, or scalable cloud deployment patterns.
Experience implementing testing, evaluation, monitoring, and feedback loops for AI applications, retrieval-augmented generation solutions, or agent workflows.
Ability to independently lead technical delivery and communicate AI solutions in clear business terms to technology and operational stakeholders.

Nice To Haves

Bachelor’s degree in Computer Science, Engineering, Information Systems, Data Science, Artificial Intelligence, a related technical field, or equivalent experience.
Experience supporting customer-facing digital platforms, authenticated portals, customer self-service, or service operations workflows.
Experience with enterprise platforms such as CRM, Drupal CMS, digital asset management, service management, marketing technology, knowledge management, contract management, or procurement systems.
Experience designing reusable AI reference architectures, accelerators, prompt libraries, multi-agent workflows, tool-using agents, context engineering, agent memory, and human-in-the-loop processes.
Experience working with distributed engineering teams, vendors, contractors, or implementation partners, including defining metrics for adoption, productivity, customer experience, operational savings, and return on investment.
Demonstrates willingness and capability to leverage emerging technology, automation, and AI tools to improve efficiency, quality, and speed. Exercises sound judgment, creative thinking, and accountability for outcomes.

Responsibilities

Design and deliver AI-powered applications, agents, copilots, task assistants, and workflow automations that improve digital product delivery, customer self-service, support operations, knowledge retrieval, vendor management, and internal productivity.
Integrate AI services with customer portals, custom applications, workflow and service management platforms, knowledge and analytics systems, procurement and contract lifecycle processes, and AWS services.
Lead AI solutions from business discovery and rapid prototyping through production deployment, adoption, performance measurement, and continuous improvement.
Translate business needs into scalable technical designs in partnership with Digital Experience, Customer Experience, Service Operations, Product, Platform Engineering, Vendor Management, and other stakeholders.
Define reusable engineering patterns for prompt frameworks, retrieval-augmented generation, text-to-SQL, semantic data models, agent workflows, evaluation, guardrails, human review, and workflow orchestration.
Build secure, reliable, observable, and cost-effective AI applications using modern software engineering practices, APIs, Model Context Protocol, agent-to-agent services, cloud services, automation frameworks, and enterprise integration patterns.
Measure solution value through automation rate, adoption, accuracy, customer satisfaction, productivity improvement, operational savings, and return on investment, while mentoring engineers, contractors, and implementation partners.