Job description
We are growing! We are currently looking to hire a Freelance Data Scientist / NLP Engineer – Text Analytics & Sentiment Analysis to work with us remotely for a period of 4 months.
Who we are:
Founded in 2006, we’re proud to be a global business. From Shanghai to Paris, we have 12 offices and operate across four continents in 70 countries. We are home to over 250 professionals from around the world, working together to serve more than 230 luxury clients.
At CXG, we love to evolve, elevate, and transform experiences while bringing brand promises to life. We offer strategic solutions that impact performance and elevate the customer experience of some of the world’s most iconic premium and luxury brands.
What you will be doing:
As part of its data solution industrialization initiatives, the company aims to design, train, and deploy text analytics and sentiment classification models within its Snowflake environment. The consultant will be involved from requirements definition to production deployment, working in the Data & AI team.
Your duties will also involve:
- Analyze business needs and define use cases for text analytics (e.g., customer feedback, support tickets, survey responses).
- Collect, clean, and prepare structured and unstructured text data in Snowflake.
- Design, train, and evaluate NLP models, including: Sentiment analysis - Text classification - Keyword extraction / topic modeling
- Develop processing workflows.
- Deploy models within the Snowflake environment (Snowpark / UDF / UDTF).
- Create documentation and provide knowledge transfer to internal teams.
What you will bring along:
- Strong expertise in NLP / Text Analytics (Python, spaCy, Hugging Face, Transformers, etc.)
- Proven experience building sentiment analysis and text classification models
- Solid knowledge of Snowflake, including: - Snowpark (Python) - Development of UDF/UDTF functions - Integration with external stages & warehouses
- Proficiency in Python (pandas, numpy, scikit-learn, ideally MLflow)
- Experience with data pipelines and orchestration tools (Airflow, dbt, Prefect, etc., depending on internal stack)
- Understanding of MLOps practices (CI/CD, model versioning, monitoring)
- Ability to work independently and structure deliverables
- Strong communication and documentation skills
- Ability to collaborate effectively with both technical and non-technical stakeholders
