Job title: Senior AI Engineer
Job type: Permanent
Emp type: Full-time
Industry: AI & Hardware
Salary type: Annual
Salary: Negotiable
Job published: 14/09/2026
Job ID: 274733

Job Description

Edison Smart is supporting a fast-growing global technology business that is making a significant investment into AI across its organisation.
We are looking for a Senior AI Engineer to help build the technical foundations behind a new generation of AI-powered applications, knowledge systems and internal workflows.
This is a highly hands-on role combining strong backend engineering with production LLM development, RAG, retrieval and knowledge infrastructure.

The Role

You will take ownership of AI solutions from initial architecture through to production, while helping establish reusable engineering patterns and infrastructure that can be leveraged across the wider organisation.

Responsibilities will include:

  • Design and build AI knowledge infrastructure, retrieval layers and context management systems.

  • Develop production-grade LLM applications and RAG pipelines.

  • Build and integrate vector databases, APIs and retrieval systems.

  • Own solutions across architecture, backend development, integration, deployment and monitoring.

  • Design scalable services primarily using Python.

  • Improve retrieval quality, token efficiency, latency, caching and overall system performance.

  • Evaluate and integrate LLM frameworks, AI development tools and third-party model APIs.

  • Translate complex or ambiguous requirements into practical AI solutions and technical roadmaps.

  • Establish reusable AI engineering standards, architecture patterns and development workflows.

  • Support and mentor junior engineers where required.

  • Work closely with technical and non-technical stakeholders to drive AI adoption across the organisation.


What We're Looking For

  • 4–7 years of Backend or Software Engineering experience.

  • 2+ years building LLM applications hands-on.

  • Strong Python development experience.

  • Production experience building AI/LLM applications beyond proof-of-concepts.

  • Strong experience with RAG architecture and retrieval systems.

  • Experience with vector databases such as Pinecone, Weaviate, Chroma or similar.

  • Experience with prompt engineering, model selection and inference pipelines.

  • Strong understanding of system design, APIs, databases, distributed systems and caching.

  • Experience owning applications through development, deployment, monitoring and troubleshooting.

  • Comfortable with basic frontend integration where required.

  • Experience using AI development tools such as Cursor, Claude Code, GitHub Copilot or similar.

  • Able to operate independently and make technical decisions in ambiguous environments.

  • Mandarin fluency is required alongside professional working English.


Nice to Have

  • Node.js or Go experience.

  • Experience designing enterprise knowledge or context-management systems.

  • Experience working with multiple LLM providers and open-source models.

  • Experience mentoring engineers or establishing AI engineering standards.

  • Experience building reusable AI platforms or frameworks used across multiple teams.

This is an opportunity to take significant ownership of production AI systems and help shape how LLM technology is built and adopted across a global technology organisation.