About the job
About the Position
Nexthink is on the forefront of integrating AI agents into the essential workflows of our Product organization. We are looking for a skilled AI Agent Engineer who will design, construct, and continually enhance intelligent agents that support and automate critical product operations functions.
This role is integral to Nexthink’s Product organization, which comprises over 30 professionals in Product Management, Product Education, Library, and Product Operations. You will work autonomously, taking full ownership of the architecture, functionality, and quality of AI agents aimed at enhancing decision-making, minimizing manual efforts, and accelerating execution.
Your work will blend applied AI engineering with strong systems thinking. The emphasis will be on production-grade agent design, assessment, governance, and workflow integration rather than model research.
This position demands a strong sense of ownership, product empathy, and the ability to operate independently in a production environment that has a tangible business impact.
Key Responsibilities
Design and Architect AI Agents
- Create reusable AI agent patterns for various Product workflows, including research synthesis, PRD (Product Requirement Document) drafting support, roadmap analysis, operational triage, and knowledge retrieval.
- Define agent instructions, tool schemas, guardrails, and structured output contracts.
- Design human-in-the-loop decision boundaries where necessary.
Integrate Agents into Product Workflows
- Incorporate AI agents into Microsoft 365, Copilot Studio, Power Platform, AWS services, and internal systems.
- Establish and maintain action interfaces between agents and deterministic systems (APIs, workflows, runbooks).
- Ensure robust orchestration across conversational and workflow layers.
Own Quality, Evaluation, and Governance
- Define measurable success criteria for agent outputs.
- Create lightweight evaluation frameworks and conduct regression testing for prompts and behaviors.
- Monitor output quality, identify hallucination risks, assess costs, and track drift over time.
- Establish safe usage guidelines and governance boundaries.
Operate and Improve in Production
- Monitor agent usage, reliability, and impact.
- Optimize performance, token efficiency, and response structures.
- Iterate on agent behavior based on real usage patterns and feedback.
- Proactively identify new opportunities for AI agents to enhance Product workflows.

