Principal Agent Engineer, Agentic AI Platform

Job Description Position Summary

Vertex is seeking an Agent Engineer, Agentic AI Platform to help create the next generation of AI agents that deliver practical value across internal and user-facing experiences. This role will focus on prototyping, building, and product ionizing multi-step agent workflows that are deeply integrated with enterprise systems, business processes, and digital products.

The ideal candidate is energized by fast-moving AI technology but grounded in strong engineering discipline. This individual will use a forward deployed engineering mindset to work closely with stakeholders, rapidly iterate on real-world use cases, connect agents to APIs and business systems, and continuously improve quality through measurement and feedback. The Agent Engineer will play an important role in shaping how AI agents are adopted and used day to day across Vertex.

• Design, prototype, and product ionize AI agents and multi-step agent workflows for internal and user-facing use cases
• Apply a forward deployed engineering approach by working closely with end users, product teams, and business stakeholders to solve real workflow problems quickly and effectively
• Build agents that can reason across steps, invoke tools, call APIs, retrieve information, and take actions within defined enterprise guardrails
• Integrate agents with internal platforms, third-party applications, enterprise APIs, and business-critical systems
• Develop reusable agent patterns, components, prompts, tools, and orchestration logic that can be scaled across use cases
• Rapidly iterate on agent behavior based on usage data, qualitative feedback, evaluation results, and operational metrics
• Improve agent quality through testing, experimentation, benchmarking, and structured measurement of outcomes
• Partner with platform, integration, data, security, and product teams to ensure agents are secure, reliable, maintainable, and aligned with enterprise architecture
• Help define best practices for agent design, tool use, fallback behavior, escalation paths, and human-in-the-loop workflows
• Support deployment, monitoring, troubleshooting, and optimization of agents in production environments
• Contribute to observability practices for agent execution, including logging, tracing, performance tracking, and issue analysis
• Ensure solutions are designed with security, compliance, and responsible AI principles in mind
• Stay current on emerging patterns, frameworks, and technologies in generative AI and agentic systems, and translate them into practical applications for Vertex

• Bachelor’s degree in Computer Science, Software Engineering, Artificial Intelligence, Data Science, or a related technical field; equivalent practical experience may be considered
• Experience in software engineering, AI engineering, machine learning engineering, or intelligent application development
• Hands-on experience building applications powered by large language models, AI workflows, or agentic systems
• Experience integrating software applications with APIs, data sources, and enterprise systems
• Demonstrated experience using AI-assisted software development and autonomous coding agents to design, generate, test, review, debug, optimize, and refactor code across complex enterprise systems.
• Deep understanding of AI-native software engineering practices and experience establishing standards, governance, and best practices for the responsible use of AI coding assistants and software engineering agents across engineering teams
• Demonstrated ability to move from prototype to production while balancing speed, quality, and operational rigor
• Experience working directly with users or stakeholders to iteratively refine technical solutions based on real-world needs
• Strong problem-solving and systems-thinking skills
• Strong written and verbal communication skills with the ability to work effectively across technical and non-technical teams

• Large language model application development
• Agentic workflow design and orchestration
• Prompt engineering and prompt iteration
• Tool use and API integration for AI agents
• Multi-step workflow automation
• Rapid prototyping and productionization
• Evaluation, testing, and quality measurement for AI systems
• Application logging, monitoring, and observability
• Distributed systems and service integration
• Secure software development practices
• Enterprise application integration
• Cloud-based application development
• Version control, CI/CD, and deployment practices

• Experience using a forward deployed engineering or similar embedded delivery model
• Experience building internal copilots, assistants, or task-oriented AI agents
• Familiarity with orchestration frameworks, agent runtimes, tool-calling architectures, and retrieval patterns
• Experience integrating with enterprise collaboration tools, workflow systems, document platforms, or knowledge repositories
• Familiarity with evaluation frameworks for AI quality, groundedness, task completion, and…