2 months ago
Ho Chi Minh City, VietnamMid Level / Senior
Responsibilities
- Design, build, and deploy end-to-end Generative AI applications, including LLM-based copilots, chatbots, RAG pipelines, multi-agent systems, and multimodal workflows.
- Develop and optimize RAG solutions using vector databases, embeddings, metadata filtering, and grounding techniques.
- Implement prompt engineering, tool and function calling, and agent orchestration for reliable task execution and workflow automation.
- Integrate GenAI solutions with enterprise systems and data sources through APIs, event-driven architectures, and secure connectors.
- Translate stakeholder requirements into technical architectures and implementation plans in collaboration with product owners and business stakeholders.
- Establish LLMOps practices covering deployment pipelines, monitoring, logging, evaluation, cost optimization, and performance tuning.
- Implement AI safety, governance, and guardrails, including content filtering, grounding validation, access control, and compliance requirements.
- Evaluate emerging GenAI models, frameworks, and tooling to improve quality, latency, and cost efficiency.
- Create reusable libraries, templates, documentation, and reference implementations to build internal GenAI capabilities.
Requirements
- Requires 3–5 years of experience in software engineering, AI engineering, ML engineering, or related fields.
- Requires at least one year of hands-on Generative AI development experience building and deploying LLM-based applications.
- Requires strong proficiency in Python and experience developing APIs and backend services.
- Requires practical experience with LLMs, embeddings, vector databases, and RAG architecture.
- Requires familiarity with GenAI frameworks such as LangChain, Semantic Kernel, LlamaIndex, or similar.
- Requires experience with cloud AI platforms such as Azure, Databricks, or NVIDIA, or equivalent platforms.
- Requires a bachelor’s degree in computer science, computer engineering, information technology, artificial intelligence, or a related discipline.
- Preferred qualifications include a master’s degree or PhD in computer science, AI, electrical engineering, physics, or a related field.
- Preferred qualifications include four or more years of AI, ML, or software engineering experience and production-grade enterprise GenAI delivery experience.
- Preferred qualifications include experience with LLMOps, MLOps, CI/CD, cloud-native architectures, and relevant Generative AI certifications.
Benefits
- Flexible hybrid working arrangement.
- Opportunities to learn and grow while developing the career you want.
- Supportive, inclusive environment focused on employee well-being and development.
- Equal opportunity employment and reasonable accommodation support during the application process.
Categories
About Manulife
Manulife is a Toronto‑headquartered public financial services company that provides life and health insurance, retirement plans, and wealth and asset management to individuals and institutions. It earns premiums and fee income from insurance, investment, and advisory products delivered across Canada, Asia, and Europe, and operates as John Hancock in the United States. Founded in 1887, the company is listed on the Toronto Stock Exchange.