AI Application Engineer

Prudential’s purpose is to be partners for every life and protectors for every future. Our purpose encourages everything we do by creating a culture in which diversity is celebrated and inclusion assured, for our people, customers, and partners. We provide a platform for our people to do their best work and make an impact to the business, and we support our people’s career ambitions. We pledge to make Prudential a place where you can Connect, Grow, and Succeed.

About the Role:

Join our global insurance leader as an AI Application Engineer! We are seeking a skilled and passionate individual to develop the AI-powered solutions that will transform our business. You'll play a crucial role in building a cutting-edge AI platform based on multi-agent system architecture, pushing the boundaries of what's possible with AI.

Job Responsibilities:

Current Context:

• Design, develop, and maintain the backend infrastructure for our AI platform, focusing on multi-agent system architecture.
• Develop and optimize prompts for large language models (LLMs) and other AI models.
• Implement and manage LLMOps/AgentOps pipelines for model training, deployment, and monitoring.
• Implement and manage relational (RDB) and NoSQL databases as needed for AI system.
• Integrate AI models and services with other platform components and applications.
• Troubleshoot and resolve AI backend issues, ensuring performance, scalability, and reliability.
• Collaborate with Data Engineers, Data Scientists, and other stakeholders to define and deliver AI-powered solutions.
• Partner with cross-functional teams globally, communicating platform updates effectively.
• Role Briefly: Multi-Agent Systems, Context Engineering (Prompt, Knowledge, Memory), LLMOps/AgentOps, HITL, AI Model Integration, Responsible AI, RDB, NoSQL, Backend Development, Vibe coding (SDD).
• Expectations for Three Months: Become familiar with our existing technology stacks, not only within your specific role but across the broader data platform ecosystem.
• Expectations Within One Year: Contribute to the development of key components of our AI platform, demonstrating expertise in multi-agent systems and prompt engineering. Specific contributions can be discussed.

Job Qualification:

• Bachelor's or Master's degree in Computer Science, Engineering, or a related fields.
• Possess 5 years or above AI/ ML engineering experiences.

Non-Technical Skills & Mindset:

• Impact-Driven & Results Focused:
  • Value-Oriented: Focused on delivering solutions that generate significant business value (millions USD impact).
  • Impact Conscious: Prioritizes work with the greatest technical and business impact. A focus on enabling data consumption through API creation is a plus.
• Growth & Learning Mindset:
  • Cross-Functional Learner: Eager to learn and understand cross-functional knowledge beyond core expertise.
  • Technology Agnostic Learner: Willing to learn new technologies and adapt to evolving landscapes.
  • Efficient Learner: Able to leverage AI tools to maximize productivity and accelerate learning.
  • Best Practice Pragmatist: Loves to follow best practices but understands trade-offs and works around limitations when necessary. Demonstrated pro-activeness through contributions to open-source projects is highly valued.
• Collaborative & Global Communicator:
  • Team Player: Collaborates effectively in global team environments. Adaptable and comfortable working within an Agile environment.
  • Excellent Communicator (English & Chinese): Fluent in both English and Chinese (Mandarin) to effectively communicate with global teams and stakeholders.

Technical Concepts:

• Fundamental computer science knowledge
• Root cause finding methodologies
• Systematic thinking
• Clean code/clean architecture principles and an aversion to over-design

Technical Skills:

• Python: Proficient in Python, with experience in AI/ML backend development.
• Agent Technologies: Experience in designing and operating production-grade agentic AI systems with secure retrieval and guardrails, including multimodal applications, multi-agent orchestration, context engineering, memory & knowledge (RAG), and MCP.SQL: Solid SQL skills for data management and querying.
• Cloud Development: Hands-on experience with GCP, including hybrid environments with on-premises DCs. Experience with AWS or Azure is also acceptable.

Technical Stacks:

• Compute & Hosting: GKE & GCE (RedHat), GCP Vertex AI
• Agentic Framework: ADK, n8n, Copilotkit, etc.
• Agentic Protocols: MCP, A2A, AG-UI, A2UI
• Databases: Redis, Firestore, PostgreSQL, Qdrant
• Data Technologies: GCP Cloud Composer (Airflow), BigQuery , Kafka Ecosystem (Confluent Cloud, Debezium, Qlik), Informatica, Power BI
• Monitoring & Observability: Langfuse, LGTM, GCP Monitoring, OTel
• CI/CD: GitHub Actions
• Infrastructure as Code: Terraform
• Security: VPC SC & Policy Tags, CMEK (KEK/DEK), Vault
• Containers: Docker, Kubernetes
• AI Tools for Development: Gemini CLI, Github Copilot

What You Can Expect:

• Global Impact: Work in a cross-country, multi-lingual environment, collaborating with teams across the globe.
• Massive Scale: Contribute to solutions that impact a large volume of customers.
• Strategic Focus: Be at the forefront of a company that strategically focuses on AI and data to drive significant value and impact.
• Cross-Functional Collaboration: Work closely with first-line business users, gaining direct insights into their needs and shaping technology solutions that address real-world challenges.
• Meaningful Technology: Make technology truly impactful, driving innovation and solving critical business problems.

Prudential is an equal opportunity employer. We provide equality of opportunity of benefits for all who apply and who perform work for our organisation irrespective of sex, race, age, ethnic origin, educational, social and cultural background, marital status, pregnancy and maternity, religion or belief, disability or part-time / fixed-term work, or any other status protected by applicable law. We encourage the same standards from our recruitment and third-party suppliers taking into account the context of grade, job and location. We also allow for reasonable adjustments to support people with individual physical or mental health requirements.