Department Manager – Data Science (Business Intelligence Center - CEO Office)

Good to know About working at CP AXTRA

📍 Location of CP AXTRA (Head Office) 3 Days : https://share.google/V5Q7MuC44FS341Xhx

📍Location of CP AXTRA Lotus’s (Nawamin Office) 1 day : https://maps.app.goo.gl/6cHYiNFfwE8EqrFU6

📍 Working style : 4 Days at the office + work from anywhere

Job description

The Data Scientist is responsible for developing predictive models, optimisation and analytical solutions across a broad range of business problems — including demand forecasting, price and elasticity modelling, customer and store segmentation, and AI/LLM-based solutions — that enable data-driven decisions across commercial and operational functions. This role bridges business needs and advanced analytics, combining strong statistical, machine-learning, and data engineering skills with the ability to source diverse data, translate complex results into clear insights, and deliver production-ready solutions. The successful candidate will be adept at understanding business requirements, building models end-to-end, telling compelling data stories, and delivering high-impact solutions on time.

Responsibilities

Modelling & Optimisation

• Design, develop, and deploy predictive and machine-learning models across areas such as demand forecasting, price and elasticity modelling, price/assortment optimisation, and recommendation
• Build customer and store segmentation, clustering, and entity-matching / item-mapping solutions to support commercial and marketing decisions
• Frame business problems as data science problems, selecting appropriate methods and validation approaches to deliver reliable, production-ready outcomes
• Continuously evaluate and improve model performance, accuracy, and business impact over time

AI & Advanced Analytics

• Apply NLP and LLM/Generative AI techniques to use cases such as text classification, sentiment/voice-of-customer analysis, data mapping, and RAG or text-to-SQL applications
• Prototype and evaluate emerging AI approaches, turning promising experiments into practical business solutions

Data, Insights & Data Sourcing

• Source, acquire, and integrate data from internal systems, third-party providers, and external sources (e.g. web scraping, APIs, public datasets)
• Explore, clean, and transform large datasets to prepare high-quality features; ensure data quality, consistency, and integrity
• Identify trends, patterns, and opportunities in data — including external factors — and proactively surface insights that drive business value

Delivery & Productionisation

• Build and maintain data pipelines and scheduled jobs (e.g. on Databricks) to run models and analytics reliably in production
• Deliver results through dashboards, reports, and applications, and maintain clear documentation of models, data, and methodologies

Business Partnering

• Engage with business stakeholders to understand objectives, gather requirements, and translate them into data science solutions

Communicate complex results clearly to technical and non-technical audiences, and manage timelines and deliverables to agreed success criteria

Key Skills & Qualifications

• Bachelor's degree (minimum); Master's degree preferred in Statistics, Mathematics, Computer Science, Data Science, Engineering, or a related quantitative field
• Minimum 3–5 years of hands-on data science experience in a commercial or enterprise environment
• Experience in retail, FMCG, or e-commerce is a strong advantage
• Strong programming skills in Python (and SQL) with solid command of data science libraries (e.g. pandas, scikit-learn, TensorFlow/PyTorch)
• Sound understanding of machine-learning and statistical techniques, with experience across several of: forecasting, elasticity/optimisation, segmentation/clustering, and entity matching
• Experience with NLP and LLM/Generative AI (e.g. embeddings, RAG, text-to-SQL) is a strong advantage
• Ability to source and integrate external data via web scraping and APIs (e.g. requests, Playwright/Selenium)
• Experience building and scheduling data pipelines, ideally on Databricks/Spark, or a similar big-data or cloud platform (Azure, AWS, or GCP)
• Strong data storytelling and visualisation skills; able to communicate insights clearly to technical and non-technical audiences
• Proven track record of delivering data science projects end-to-end, on time, and managing stakeholder expectations
• Familiarity with version control (Git) and Agile/Scrum delivery is a plus