Senior AI Platform Engineer

We are building an Agentic AI Platform within Manulife that powers nextgeneration intelligence across the enterpriseautonomous task execution reasoningbased workflows toolcalling retrievalaugmented capabilities multiagent ecosystems and safetygoverned automation.

As a Senior AI Platform Engineer for Manulife Asia you will help architect and deliver the foundational services that enable AI agents to plan reason act collaborate and integrate deeply with business systems. You will work across cloud distributed systems orchestration frameworks vector/memory stores agent workflows and safety/guardrail layers to ensure the platform is secure scalable and enterpriseready for Asia markets.

This role is ideal for engineers who blend strong systems engineering skills with curiosity for cuttingedge AI patterns.

Position Responsibilities:

1. Agentic AI Platform Architecture & Core Services

• Build platform components that power agent planning reasoning orchestration toolcalling and multistep task execution.

• Implement shared runtimes for multiagent coordination state management memory persistence and messaging.

• Design interoperable APIs/SDKs used by data scientists and developers to build agentpowered applications.

2. Retrieval Memory & Knowledge Integration

• Develop standardized retrieval frameworks (search embeddings knowledge connectors) enabling agents to access enterprise knowledge safely.

• Build and optimize shortterm memory longterm memory and episodic state abstractions for agent workflows.

• Integrate structured/unstructured data sources through unified connectors and retrieval bridges.

3. Tooling Connectors & Ecosystem Enablement

• Build tool interfaces that allow agents to invoke enterprise systems APIs databases and automations.

• Create reusable patterns for function/tool definitions schema validation safe execution rate limiting and auditability.

• Work with regional business teams to onboard Asiaspecific systems and workflows into the global agent ecosystem.

4. Agent Safety Governance & Observability

• Implement enterprise-grade guardrails: content filtering hallucination mitigation safeaction constraints and policydriven approvals.

• Build observability for agent workflows: traces reasoning logs action sequences feedback loops and performance metrics.

• Provide mechanisms for feedback oversight and ongoing evaluation of agent behaviour.

5. Cloud Infrastructure & Distributed Systems

• Develop and operate scalable backend services supporting hightraffic agent interactions retrieval operations and realtime execution flows.

• Use cloudnative technologies (containers orchestration IaC CI/CD) to deliver reliable cost-efficient services.

• Optimize runtime performance across CPU/GPU/accelerator workloads.

6. Developer Experience & Collaboration

• Build templates scaffolding and CLI tools to enable quick development of agentpowered applications.

• Partner with global engineering security and AI governance teams to localize the platform for Asias regulatory and dataresidency needs.

• Mentor data science teams on agentic design patterns and platform capabilities.

Required Qualifications:

• Above 5 years experience in backend/platform/cloud systems engineering.

• Proficiency with Python and Java/Scala/TypeScript or similar languages for building backend services and automation.

• Understanding of LLM systems retrieval architectures embeddings vector stores and prompt/tool orchestration fundamentals.

• Handson experience with cloud-native development: Kubernetes containers CI/CD.

• Strong grasp of API design asynchronous workflows concurrency and system reliability.

• Familiarity with security governance and compliance concepts related to AI or data systems.

• Ability to collaborate across global teams and translate business problems into platform capabilities.

• Bonus point if you have experience with one or more of:

  • Agent frameworks or orchestration engines.

  • Multi-agent systems task decomposition or reasoning chain design.

  • Knowledge graphs semantic search or hybrid retrieval.

  • Guardrail and evaluation frameworks for LLMs.

  • Complex workflow systems (rule engines workflow orchestrators automation platforms).

  • Background in enterprise AI or regulated environments.

When you join our team:

• Well empower you to learn and grow the career you want.

• Well recognize and support you in a flexible environment where well-being and inclusion are more than just words.

• As part of our global team well support you in shaping the future you want to see

About Manulife and John Hancock

Manulife Financial Corporation is a leading international financial services provider helping people make their decisions easier and lives better. To learn more about us visit is an Equal Opportunity Employer

At Manulife/John Hancock we embrace our diversity. We strive to attract develop and retain a workforce that is as diverse as the customers we serve and to foster an inclusive work environment that embraces the strength of cultures and individuals. We are committed to fair recruitment retention advancement and compensation and we administer all of our practices and programs without discrimination on the basis of race ancestry place of origin colour ethnic origin citizenship religion or religious beliefs creed sex (including pregnancy and pregnancy-related conditions) sexual orientation genetic characteristics veteran status gender identity gender expression age marital status family status disability or any other ground protected by applicable law.

It is our priority to remove barriers to provide equal access to employment. A Human Resources representative will work with applicants who request a reasonable accommodation during the application process. All information shared during the accommodation request process will be stored and used in a manner that is consistent with applicable laws and Manulife/John Hancock policies. To request a reasonable accommodation in the application process contact .