AI Operations Engineering Specialist
Penbrothers
Get more replies from employers
Send a job-specific resume in minutes.
Benefits offered by this job
Job summary
Penbrothers is hiring for an AI Operations & Agent Engineering Specialist to design, build, and scale a MAS ecosystem focused on governance, risk, and compliance automation. You will architect parent-child agent systems, integrate with enterprise tools, and ensure reliable, auditable operation across environments.
This hybrid role is based in Manila time zone. The candidate should have 2–3 years in AI-powered automation, strong prompt engineering, and solid scripting ability, with focus on agent
Qualifications
- 2–3 years of experience developing, configuring, operating, or supporting AI-powered automation, agentic workflows, or LLM-based solutions.
- Hands-on experience with AI agents, prompt engineering, workflow design, and troubleshooting AI system behavior.
- Experience documenting technical designs, dependencies, limitations, and operational procedures; strong troubleshooting mindset.
Responsibilities
- Design, build, and maintain AI agents to support governance, compliance, and knowledge workflows.
- Deploy, configure, and maintain AI agents across development, testing, and production environments.
- Monitor MAS performance, reliability, and latency; create operational dashboards.
- Investigate and resolve agent failures and incorrect outputs; perform root-cause analysis.
- Build integrations between AI agents and enterprise tools and data sources.
Skills
Tools
Job description
Penbrothers is an HR and remote talent management partner and one of the fastest-growing companies in the Philippines. We connect talented Filipinos to global opportunities with high-growth startups and dynamic companies, enabling them to build careers from the comfort of their own homes. We provide end-to-end support in recruitment, HR, payroll, compliance, and employee engagement - creating an environment where talent can thrive and global companies can grow.
Our client is a global leader in digital trust, PKI, and machine identity management, helping organizations manage and secure keys, certificates, and identities across cloud, containers, and enterprise environments. As digital ecosystems grow, we enable secure, scalable, and automated cryptographic operations.
Our client is building a next-generation Governance, Risk, and Compliance Automation Team focused on leveraging Artificial Intelligence and Multi-Agent Systems (MAS) to transform how compliance, governance, assurance, and related knowledge work are enabled. The AI Operations & Agent Engineering Specialist will be the technical operator and builder responsible for developing, growing, maintaining, and improving the MAS ecosystem.
This role is focused exclusively on AI agent systems. The specialist will design and maintain parent-agent and child-agent architectures or AI "Brain" architectures, agent orchestration patterns, integrations, monitoring, troubleshooting, documentation, and technical enablement needed to make the MAS reliable, scalable, and useful for business stakeholders. Knowledge of governance, risk, and compliance (GRC) is important because the MAS will support compliance and governance use cases, but this role will not perform traditional GRC activities, audit execution, control testing, risk register ownership, or compliance assessment work.
This is not a Compliance Analyst role and not a general automation role. The Compliance Analyst determines what governance or compliance workflows need support. The AI Operations & Agent Engineering Specialist determines how the Multi-Agent System is designed, built, operated, troubleshot, and scaled to enable those workflows.
Multi-Agent System Development: Design, build, and maintain AI agents that support governance, compliance, business assurance, knowledge retrieval, and decision-support workflows. Develop parent-agent and child-agent architectures that support orchestration, routing, task delegation, and consistent outputs. Implement agent-to-agent communication patterns, workflow coordination, and reusable agent templates. Build agent instructions, prompts, tools, actions, connectors, knowledge sources, and escalation logic.
AI Agent Platform Operations: Deploy, configure, and maintain AI agents in development, testing, and production environments. Manage agent lifecycle activities, including onboarding, versioning, release notes, performance tuning, regression testing, and retirement. Monitor MAS performance, reliability, accuracy, latency, failure rates, and execution consistency. Maintain technical documentation for agent architecture, dependencies, access requirements, data sources, integrations, and expected behavior. Create operational dashboards or reports showing MAS health, usage, adoption, and reliability metrics.
Agent Troubleshooting & Reliability Engineering: Investigate and resolve agent failures, incorrect outputs, broken workflows, tool execution errors, integration failures, and data access issues. Perform root cause analysis for MAS incidents and implement corrective actions. Improve agent resilience through better prompts, improved routing, guardrails, fallbacks, error handling, and validation steps. Test agents against realistic scenarios and edge cases before release.
AI Integration Engineering: Build and maintain integrations between AI agents and approved enterprise tools, systems, repositories, and data sources (such as Microsoft 365, SharePoint, Confluence, Microsoft Graph, and APIs). Support secure retrieval, summarization, routing, and output generation. Develop and maintain MCP-based or equivalent tool integrations where approved and appropriate.
Agent Governance Enablement: Maintain the MAS technical inventory, including agents, agent owners, purpose, linked knowledge sources, connected tools, permissions, and production status. Implement technical controls required by internal AI governance processes, including logging, monitoring, change tracking, access boundaries, approval gates, and shutdown/pause procedures. Ensure agents are built to support human oversight, traceability, repeatability, and auditability.
- Owning or maintaining risk registers.
- Performing control testing or audit execution.
- Managing compliance assessments or certification programs.
- Responding directly to customer questionnaires as a compliance owner.
- Serving as the control owner for ISO, SOC 2, PCI DSS, or other frameworks.
- Building non-AI workflow automation unrelated to MAS capability, reliability, or enablement.
- Acting as the primary author of policy, procedure, or framework content unless directly supporting agent behavior or MAS documentation.
Experience: 2-3 years of experience developing, configuring, operating, or supporting AI-powered automation, agentic workflows, or LLM-based solutions.
Core Competencies: Hands-on experience with AI agents, prompt engineering, workflow design, and troubleshooting AI system behavior. Experience working with APIs, data connectors, knowledge repositories, and enterprise collaboration platforms. Demonstrated ability to document technical designs, dependencies, limitations, and operational procedures. Strong troubleshooting mindset.
Technical Skills: Microsoft Copilot Studio, Microsoft Power Platform, Azure AI Services, or similar AI workflow platforms. Enterprise LLM platforms (ChatGPT Enterprise, Claude, Azure OpenAI). Prompt engineering, agent instructions, and tool/action configuration. REST APIs, Microsoft Graph, SharePoint, Confluence, GitHub, and structured repositories. Python, JavaScript, or similar scripting experience. MCP servers or comparable agent-tool integration patterns strongly preferred.
Preferred Knowledge: Familiarity with GRC terminology and workflows; exposure to ISO 42001, ISO 27001, SOC 2, or AI governance; awareness of OWASP Top 10 for LLMs and AI security risks.
Level of Authority: Operational and technical authority to design, build, test, troubleshoot, document, and recommend improvements or lifecycle changes (promote, pause, redesign, retire) for approved MAS agents and technical components. May not independently approve new AI use cases, change governance policy, accept compliance risk, or deploy agents that bypass required approvals. Must elevate material security, access, data, reliability, or governance concerns.
4pm-12mn Manila time
We use AI tools to streamline our application process - including an initial conversation with an AI Interviewer. All hiring decisions are made entirely by humans: our Talent Acquisition team guides your full candidate journey and makes all evaluation decisions.
You are welcome to use AI for CV refinement and research, but real-time AI assistance during interviews or skill assessments is strictly prohibited to ensure an authentic evaluation.
Read our full AI Disclaimer to learn more.
At Penbrothers, we are obsessed with creating positive employee experiences. Here you’ll find an environment that nurtures learning and provides opportunities for growth. You’ll have the opportunity to make an impact on fast-growing startups and dynamic companies.
- Meaningful work & Growth: We take every opportunity to stretch ourselves and deliver an excellent client experience.
- Employee as our biggest asset: We are genuinely invested in our people’s career and welfare.
- Global reach & local impact: Get to work with high-growth startups and dynamic companies from the comfort of your own home.
- Powering global startups: We've created 1,400 Filipino jobs that empower global start-ups to focus on growth.
'/%3e%3cpath%20d='M101.744%2012.4726L102.894%2016.1947L99.0021%2013.2201L101.744%2012.4726ZM105.3%208.40937H100.488L99.0026%203.59473L97.5116%208.41047L92.7%208.40385L96.5965%2011.3834L95.1055%2016.1942L99.0021%2013.2196L101.408%2011.3834L105.3%208.40992V8.40937Z'%20fill='white'/%3e%3cdefs%3e%3clinearGradient%20id='paint0_linear_5593_1381'%20x1='90'%20y1='9.44471'%20x2='99'%20y2='9.44471'%20gradientUnits='userSpaceOnUse'%3e%3cstop%20stop-color='%2300AD70'/%3e%3cstop%20offset='0.998594'%20stop-color='%2300B67A'/%3e%3cstop%20offset='1'%20stop-color='%23DCDCE6'/%3e%3c/linearGradient%3e%3c/defs%3e%3c/svg%3e){kind=small}
