Senior Data Scientist

Job Description

Coders Connect are partnering with Sanofi .

Sanofi (NYSE : SNY) is a leading global integrated healthcare company that discovers, develops, and distributes therapeutic solutions to improve the lives of everyone.

The company works to prevent and treat the diseases of today, as well as those we may face tomorrow. With over 100,000 dedicated professionals in more than 100 countries, Sanofi is devoted to advancing healthcare around the world.

Sanofi operates across multiple therapeutic areas including General Medicines, Specialty Care, Vaccines and Consumer Healthcare.

Equal opportunity employer. Sanofi is an equal opportunity employer that embraces diversity to foster positive, innovative thinking that will benefit people worldwide.

Sanofi is also committed to employing qualified individuals with disabilities and, where warranted, will provide reasonable accommodation to applicants, as well as its employees.

Consumer healthcare (CHC) business unit. The role will regard Sanofi’ Consumer Healthcare. Becoming a standalone division, Consumer Healthcare’s purpose is to serve healthier, fuller lives by offering moments of relief to our Patients & Consumers in our key platforms, including Allergy, Physical & Mental Wellness, Pain, Digestive Health.

CHC does business in 133 countries; 4000 professionals work in marketing, sales and services teams. Learn more at www.sanofi.

com / en / your-health / consumer-healthcare .

Consumer Healthcare is becoming a standalone division within Sanofi in order to become a faster moving, consumer and customer centric business as part of project CHLOE (Consumer HealthCare Lead Optimize Empower).

This business and IT transformation will entail a standalone ERP, Financial, Systems, Regulatory and People.

Global Digital Team. The team is charged with accelerating the shift to precision marketing and to e-commerce sales, scaling best-in-class data driven decision making tools, capturing new opportunities in the digital health space and uphauling disjointed commercial systems. T

his team leverages both dedicated expertise internally at Sanofi, and delivery and deployment partners. It builds products, runs service / outsourcing contracts, and develops centers of excellence in technology and digital.

IShift . IShift is the new generation of SAP S4 / HANA, with one common framework across Sanofi BUs and geographies replacing JDEdwards in the US, OEP and unity in all other geographies.

POSITION OVERVIEW

This position reports to the Head of Advanced Analytics in the CHC business unit in Sanofi

• A cornerstone of CHC transformation in the coming years, the Senior Data Scientist will play a key role for shaping the core data capabilities that drive critical use cases within CHC organization.
• We are looking for an energetic, focused, and skilled senior data scientist with strong data and information management, business analytics and communication skills to help improve the business process of CHC’s global functions, IA and Supply Chain area.
• In this role, you will drive critical business impacts. You will play a key role to drive end-to-end solutions from understanding the business requirements of CHC, exploring a large amount of historical data, build ML predictive forecasting models, building prototypes and exploring conceptually new solutions collaborating with Sanofi’s Data Science team and partners.
• You will collaborate closely with research scientists, engineering peers as well as business stakeholders. You will be at the heart of a growing and exciting focus area for CHC business.
• The candidate must be able to work independently and collaboratively

You will work with a diverse team of business analysts, data scientists, technical engineers, data architects, and project managers to deliver outcomes aligned with our business need.

KEY RESPONSIBILITIES

Senior Data Scientist will be responsible for :

• Build Machine Learning and AI models to generate business value.
• Identify the business need and deep diving into forecasting issues using SQL and scripting languages like R, Python, and internal dashboards to drive short term fixes and long-term improvements.
• Lead modeling efforts from conceptualization to implementation, keeping all relevant partners informed.
• Building reusable tools to streamline the modeling pipeline and sharing knowledge
• Researching & implementing state of the art and traditional modeling techniques including tree-based models, Deep Learning, linear models, unsupervised methods, embeddings, representations, and clustering.
• Turn all technical outcome to a simple storyline to explain the solution to the CHC business leads.
• Supervising daily execution and delivery from start to completion involving deadlines, achievement, and processes; engaging vital and appropriate resources across product lines and shared services per solution blueprint and align IT capacity with top business priorities.
• Act as a subject matter expert in the design and recommendation of analytical methodologies and approaches
• Able to interact with business teams and stakeholders.
• Proven experience in Machine leaning and Statistical learning oriented to forecasting.
• Ready to do maintenance, debug, refactoring, unit-testing, integration testing, packaging and documentation of large-scale python projects.
• GitOps and MLOps skills oriented to CICD.
• Be able to Customize Databricks Clusters and Jobs in order to perform Big Data tasks using spark.
• Be able to do maintenance of the smtp email delivering service.

Requirements

• Experience working in FMCG
• Experience using scripting languages such as Python or R, and common libraries such as scikit-learn, pandas, xgboost, etc.
• Experience applying & implementing solutions with the following data science concepts and domains : Classification, Regression, Deep Learning, NLP, Feature Engineering
• 3+ years of hands-on experience working with large scale data and advance analytics life cycle, including data discovery, business intelligence, data quality management, metadata management, and related disciplines.
• Hands-on experience with relational databases, data warehouses, operational data stores, in-memory databases, SQL and noSQL technologies and concepts.
• Problem-solving skills, creative thinking, and ability to implement creative solutions that tackle business problems.
• Agile ways of working and large projects phased delivery

Data & Business intelligence domain and software experience is a plus :

• Experience of Interfacing heterogeneous systems and data sources
• Experience in cloud computing platforms like AWS or Azure
• Experience in Re-clustering of data and Micro-Partitioning in Snowflake
• Experience in data mining, forecasting, simulation, and / or predictive modeling
• Working knowledge in Informatica IICS, Power BI and Tableau
• Working knowledge of procuring data from ERPs (SAP, JDE, etc.)
• Python dev : scripting and OOD experience, python unit testing, linting, HTTP request, code packaging, Dockerizing
• Git : Github CICD governance (github pipelines, github actions and github projects tools)
• AWS tools : S3 Buckets, Lambda functions, ECR, EC2, Secrets Manager
• Databricks environment UI and DB APIs (databricks API, db connect)
• ML & Forecasting : Facebook Prophet, DeepAR, Linear & non-linear models, decision Trees, spark MLlib, scikit-learn
• Hyperparameter tunning & feature selection : spark UDFs and Hyperopt
• Model Governance : Mlflow UI and API

Education

• Bachelors degree
• Six Sigma certification is preferred
• Fluent in English

Requirements

Experience working in FMCG Experience using scripting languages such as Python or R, and common libraries such as scikit-learn, pandas, xgboost, etc.

Experience applying & implementing solutions with the following data science concepts and domains : Classification, Regression, Deep Learning, NLP, Feature Engineering 3+ years of hands-on experience working with large scale data and advance analytics life cycle, including data discovery, business intelligence, data quality management, metadata management, and related disciplines.

Hands-on experience with relational databases, data warehouses, operational data stores, in-memory databases, SQL and noSQL technologies and concepts.

Problem-solving skills, creative thinking, and ability to implement creative solutions that tackle business problems. Agile ways of working and large projects phased delivery Data & Business intelligence domain and software experience is a plus : Experience of Interfacing heterogeneous systems and data sources Experience in cloud computing platforms like AWS or Azure Experience in Re-clustering of data and Micro-Partitioning in Snowflake Experience in data mining, forecasting, simulation, and / or predictive modeling Working knowledge in Informatica IICS, Power BI and Tableau Working knowledge of procuring data from ERPs (SAP, JDE, etc.

Python dev : scripting and OOD experience, python unit testing, linting, HTTP request, code packaging, Dockerizing Git : Github CICD governance (github pipelines, github actions and github projects tools) AWS tools : S3 Buckets, Lambda functions, ECR, EC2, Secrets Manager Databricks environment UI and DB APIs (databricks API, db connect) ML & Forecasting : Facebook Prophet, DeepAR, Linear & non-linear models, decision Trees, spark MLlib, scikit-learn Hyperparameter tunning & feature selection : spark UDFs and Hyperopt Model Governance : Mlflow UI and API Education Bachelor's degree Six Sigma certification is preferred Fluent in English