Software Engineer III; Agentic AI
Listed on 2026-09-03
-
Software Development
AI Engineer (Applied/Software), Backend Developer
Software Engineer III – Agentic Acceleration Group
At UKG, the work you do matters. The code you ship, the decisions you make, and the care you show a customer all add up to real impact. Today, tens of millions of workers start and end their days with our workforce operating platform. Helping people get paid, grow in their careers, and shape the future of their industries. That's what we do.
We never stop learning. We never stop challenging the norm. We push for better, and we celebrate the wins along the way. Here, you'll get flexibility that's real, benefits you can count on, and a team that succeeds together. Because at UKG, your work matters—and so do you.
*** UKG is unable to offer sponsorship for this position.***
We are looking for a Software Engineer III to join our Agentic Acceleration Group and help build and scale agentic AI capabilities on Google's Agent Development Kit (ADK) and other enterprise agentic platforms. This role provides an opportunity to contribute to cutting-edge agentic AI systems, intelligent automation workflows, and impactful software solutions used by enterprises and users worldwide. As a Software Engineer III, you will own the development of agent-powered features and projects, contribute to technical design decisions, and help establish modern agent development practices.
You will be responsible for the design, development, testing, deployment, and maintenance of complex agentic systems built on established AI platforms, working collaboratively with product, architecture, and engineering partners.
Responsibilities
- Agent Development:
Design, build, test, and deploy production-grade AI agents using Google ADK and other agentic platforms such as the Anthropic Claude SDK and Lang Graph. Write clean, maintainable, and efficient code for agent workflows, tool integrations, and multi-agent orchestration. - Platform Integration:
Build agents that integrate with enterprise systems through tools, APIs, and Model Context Protocol (MCP) servers. Implement custom tools, skills, and plugins that extend agent capabilities across UKG's HCM platform. - Feature and Project Delivery:
Own execution and delivery of agent-powered features and projects, working with product management and engineering partners to clarify requirements, manage priorities and timelines, and deliver high-quality results. - Technical Design:
Participate in design reviews with peers, architects, and stakeholders. Contribute to the design of complex agentic systems and applications, including multi-agent coordination patterns, task delegation workflows, and agent communication protocols, with attention to performance, scalability, reliability, and maintainability. - Code Review and Engineering Practices:
Review code developed by other engineers, provide constructive feedback, and help maintain a high bar for technical excellence, including clean coding practices, appropriate design patterns, unit testing, and observability built from the ground up. - Service Health and Quality:
Maintain the health and quality of agent-powered services by proactively identifying and addressing issues. Use service health indicators, agent performance metrics such as task success rates, latency, and cost, and telemetry to recommend improvements. Conduct root cause analysis for agent failures and help implement measures to prevent recurrence. - Agent Operations:
Support agent deployment, monitoring, and lifecycle management. Apply practices for agent versioning, cost monitoring, performance optimization, and iterative improvement. Build observability into agent workflows, including execution tracing, decision logging, and failure analysis. - Testing and Evaluation:
Build testable agents and agentic systems; define and automate tests using appropriate frameworks. Apply agent-specific testing strategies, including prompt validation, agent evaluation, multi-step workflow testing, tool invocation testing, tool validation, and adversarial scenario testing. - Dev Ops Model:
Take ownership across the software lifecycle—from collaborating with product management on requirements through design, development, testing, deployment, and maintenance of software in…
(If this job is in fact in your jurisdiction, then you may be using a Proxy or VPN to access this site, and to progress further, you should change your connectivity to another mobile device or PC).