Technical Analyst / AI Data Engineer

Key Responsibilities

• Design and build resilient data infrastructure on on-premise or clouds using industry standard tools

• Build data pipelines that clean, transform, and aggregate data from disparate sources, including messaging queues, RDBMS, etc.

• Ensure data integrity and scalability through enforcement of data standards, setting up quality checks, monitoring pipelines, and maintaining data accuracy and accessibility

• Develop and scale RAG architectures, integrating LLM APIs, vector databases, retrieval mechanisms, and embedding models for efficient knowledge retrieval.

• Design robust infrastructure to support multi-agent interactions (e.g., LangChain/ Langgraph, AutoGen/ MCP (Model Context Protocol) ), enabling efficient message passing, distributed decision-making, and autonomous collaboration.

• Design, implement, and maintain structured and unstructured knowledge bases, including knowledge graphs, ontologies, and text embeddings, to enhance LLM output quality with domain-specific data and automated indexing.

• Utilize vector databases, NoSQL databases, and graph databases to support efficient knowledge retrieval and AI workloads.

• Collaborate with AI researchers, ML engineers, and software developers to integrate AI models into production environments effectively.

• Design clear, structured prompts, optimizing AI responses through iterative refinement and advanced techniques like few-shot learning and chain-of-thought reasoning for improved accuracy and coherence.

• Ensure best practices for data privacy, security, and compliance in AI deployments.

• If experienced in frontend development, build product prototypes or core features using common frameworks (React, etc.).

• If experienced in backend development, design interfaces and manage databases using Python, participating in microservice or containerization projects (Docker/K8s).

• Effectively use various existing AI tools or solutions (such as ChatGPT, GitHub Copilot, Cursor, etc.) to improve development efficiency.

• Work closely with design, product, and operations teams, flexibly utilizing the latest AI tools and technologies to accelerate product iteration cycles.

• Validate product innovation points and technical feasibility through rapid PoC (Proof of Concept) and MVP (Minimum Viable Product).

Preferred Qualifications

• Degree in Computer Science, Mathematics, Statistics, or related field
• Strong programming skills in Python, Java, Scala or C++, Frontend (React, NextJS, etc.).
• Minimum 2-3 years of experience with machine learning and artificial intelligence technologies, preferably in AI agent development.
• Preferred knowledge of large language models and natural language processing.
• Experience in developing autonomous AI agents or Agentic AI systems, highly desirable given the role’s focus on Agentic AI initiatives.
• Experience in leveraging structured and semi-structured data to improve LLM-generated outputs.
• Deep understanding of AI Agent ecosystems and experience with frameworks such as AutoGen, LangChain / Langgraph, MCP (Model Context Protocol)
• Expertise in designing, testing, and optimizing prompts, including advanced techniques like COT (Chain-of-Thought), TOT (Tree-of-Thought) etc.
• Experience with distributed computing and cloud platforms such as Microsoft Azure and Alibaba Cloud.
• Solid Experience in building or maintaining Spark batch and streaming data pipelines with CI/CD processes and DevOps tools such as Git, Docker, k8s.
• Familiarity with Streaming processes (e.g. Kafka, Rabbitmq), data modeling, and database design principles.
• Proactive and collaborative approach, with strong problem-solving, critical thinking, and communication skills.

Fluency in written and spoken English and Cantonese; Mandarin is an advantage.