Senior Software Engineer, AI Applications

LFX Digital; Hong Kong; On-site; HKD 900,000 - 1,200,000; Full time

Job summary

LFX Digital, a Fung Group company, seeks a hands-on senior software engineer to build and operate SDU applications. You will own services end to end—design, build, deploy, monitor, and maintain—with ~one third dedicated to integrating AI/ML capabilities into the stack.

You’ll work on data pipelines, AI/ML integration, and production systems across the supply chain domain, in a fast-paced environment that emphasizes practical AI deployments and cost efficiency.

Qualifications

• Bachelor's degree in CS or related field.
• 5+ years of professional software engineering with Python.
• Strong API design, debugging, testing, and version control fundamentals.
• Relational and graph databases (SQL, GraphDB) experience.
• Experience with containerisation and cloud deployment (Docker, Kubernetes) and CI/CD.
• Practical familiarity with ML frameworks (PyTorch, scikit-learn) and open-source LLMs.

Responsibilities

• Design, build, and ship backend services and APIs supporting SDU data and supply chain products.
• Own data pipelines and integrations across internal systems and external sources.
• Integrate foundation models and ML components, focusing on RAG architectures.
• Deploy, monitor, and maintain production AI-enabled applications; manage reliability and costs.

Skills

Python

API design

SQL

CI/CD

Data pipelines

ML frameworks

LangChain

PyTorch

Education

Bachelor's degree in computer science or related field

Tools

Neo4j/AWS Neptune

GraphDB

Docker

Kubernetes

Job description

LFX is a Fung Group company, which focuses on being an incubation, investment, and operating platform providing digital solutions and digitally enabled services across the end-to-end consumer goods supply chain.

See https://lfxdigital.com/

Job Description

We're looking for a hands‑on senior software engineer to build and run the applications that power the Strategic Data Unit (SDU). This is primarily an engineering role: you’ll own services end to end — design, build, deploy, monitor, and maintain — with roughly a third of your time spent integrating AI/ML capabilities into those systems. If you enjoy shipping production software that people depend on daily, and want AI to be a meaningful part of the stack rather than the whole job, this is a good fit. The work sits close to real supply chain problems across the LFX Group, so what you build has visible operational impact.

Key Responsibilities

Application Development

• Design, build, and ship backend services and APIs that support SDU data and supply chain products.
• Write clean, tested, reviewable code; participate in design reviews and code reviews as a matter of routine.
• Build and maintain data pipelines and integrations across internal systems and external vendor/partner sources, utilizing both relational and graph databases (GraphDB) to accurately model and query complex supply chain networks.
• Develop internal tools and interfaces that make data and models usable by non‑technical business teams.

Maintenance and Operational Ownership

• Own deployed services: monitoring, alerting, logging, incident response, and root‑cause follow‑up.
• Debug and resolve production issues, including the unglamorous ones — data quality breaks, upstream schema changes, silent failures, and vector/graph index synchronization issues.
• Refactor and pay down technical debt; improve reliability, performance, and cost efficiency of existing systems.
• Maintain clear documentation, runbooks, and handover notes so systems remain supportable by others.
• Manage CI/CD pipelines, containerised deployments, and environment configuration.
• Apply sensible security, access control, and data handling practices, particularly for vendor and client data.
• Contribute to shared standards, tooling, and conventions within the team.

AI/ML Integration

• Integrate foundation models and ML components into production applications, with a heavy focus on building and optimizing Retrieval‑Augmented Generation (RAG) architectures.
• Leverage knowledge graphs (GraphDB) alongside traditional vector search to enhance the factual grounding and contextual reasoning of our AI features.
• Deploy, serve, and maintain models in production, managing prompt design, evaluation, guardrails, and cost/latency; fine‑tune open‑source models where a task genuinely warrants it.
• Build and maintain pipelines using tools such as HuggingFace, LangChain, and image generation models where applicable to business needs.
• Assess new AI capabilities pragmatically: identify where they solve an actual business pain point, and where conventional software is the better answer.

Job Requirements

• Bachelor's degree or above in computer science, engineering, or a related field.
• 5+ years of professional software engineering and maintenance experience, with strong Python skills.
• Solid grounding in software fundamentals: API design, version control, testing, debugging, as well as deep familiarity with relational databases (SQL), graph databases (e.g., Neo4j, AWS Neptune), and vector stores.
• Working knowledge of containerisation and cloud deployment (Docker, Kubernetes, or equivalent); CI/CD experience.
• Practical familiarity with ML frameworks (PyTorch, scikit‑learn) and the current generative AI ecosystem (open‑source LLMs, HuggingFace, LangChain), with proven experience taking RAG applications from proof‑of‑concept to production.
• Demonstrated experience operating and maintaining production systems, not only building prototypes.
• Ability to communicate clearly with non‑technical stakeholders and adapt as business needs shift.
• Fast learner, comfortable in a fast‑paced environment with shifting priorities.