Data AI Engineer – AI Search & Chat
Data AI Engineer – AI Search & Chat
About the team. The Data, AI, and Innovation team leads data, AI and innovation for Central Retail Corporation at group level. These roles build the data and AI foundation of Central Retail's strategic e-commerce platform, working across personalization, search and customer analytics.
AI-first is mandatory. Every member of the team is expected to use AI in coding and in daily work — AI coding assistants and agents for building, testing and reviewing; AI tools for analysis, writing and research. Candidates must show how they already work this way, and we assess it in the interview.
How we work
Small, hands-on squad; everyone ships code or data products to production.
Use cases first: we start from a business problem and a metric, then pick the tool.
AI-native workflow: AI-assisted coding, review and documentation are the default, not optional.
Strong partnership with business unit commercial, marketing and product teams across the group.
Modern stack on GCP (BigQuery, Cloud Run, Vertex AI), Python, SQL, but not strict.
Role summary. You build the AI that helps customers find and buy: semantic product search and a shopping chat assistant on Central Retail's strategic e-commerce platform. You take models from prototype to production and are measured on relevance, conversion and reliability, not demos.
What you will do
Build and improve product search: hybrid keyword + vector retrieval, query understanding (Thai/English, typos, synonyms), ranking and re-ranking.
Build the conversational shopping assistant: RAG over catalog, promotions and store content; tool calling for stock, price and order lookups; safe fallbacks and human hand-off.
Use behavioral signals from the tracking pipeline and personalization layer to rank results per customer.
Own evaluation: offline relevance sets, LLM-as-judge and human review, guardrail tests, and online A/B tests with the BI analyst.
Ship and operate services on GCP (Cloud Run, Vertex AI, BigQuery, vector search) with monitoring for latency, cost and quality.
Improve product data where it limits search: attribute extraction and enrichment with LLMs.
Document and share patterns so other CRC teams can reuse them.
What you bring
3–7 years in ML, search or backend engineering, with at least 1–2 years shipping LLM or search features to real users.
Strong Python; production APIs (FastAPI or similar); containers and CI/CD.
Hands-on with embeddings, vector databases, RAG, prompt and tool design, and at least one major LLM API.
Search fundamentals: BM25, learning-to-rank or re-rankers, relevance metrics (NDCG, MRR, recall).
Experience designing evaluations and reading A/B results honestly.
Works AI-first: agentic coding tools (e.g. Claude Code, Cursor, Copilot) are part of the daily workflow for building, testing and reviewing code — mandatory for this role.
Comfortable with Thai-language text processing, or eager to learn it fast.
Nice to have
E-commerce search or recommendation experience; Elasticsearch/OpenSearch or Vertex AI Search; fine-tuning small models; LINE chat integrations.