Ingénieur Data

About

The Institut de Cancérologie de l'Ouest (ICO) Nantes-Angers is a center of excellence in cancer care and research. Labeled Comprehensive Cancer Center (CCC) by the Organization of European Cancer Institutes (OECI), the ICO is the leading cancer research center in the provinces of France and the third nationally after Institut Gustave Roussy (Villejuif) and Institut Curie (Paris) in terms of patient activity and clinical trial enrollment. Its radiotherapy activity is also the largest in France with 90,000 sessions per year.

For 5 years, the ICO has placed Real-World Data (RWD) and AI at the center of its research and innovation strategy. Its Data Factory & Analytics department is a multidisciplinary, integrated structure dedicated to the collection, qualification, analysis, and valorization of data generated during the care of our patients. The department ensures complete control over the data lifecycle, from its production during patient care within the ICO to its analysis and valorization. It manages the construction, population, and qualification of several data warehouses (EDS), infrastructures, and national programs: the ICO's local EDS, which aims to enable the reuse of RWD for research and organizational activity management; the national CONSORE program (Continuum of Care and Research) in conjunction with the federation of 19 cancer research centers in France (Unicancer); the national EDS OncoDS (Onco Data Share), winner of the Health Data Hub 2023 call for projects dedicated to supporting the creation of hospital EDS; the inter-regional EDS, Ouest Data Hub, in conjunction with the University Hospitals of Rennes, Brest, Nantes, Angers, Tours, and Orléans (GCS HUGO - University Hospitals of the Greater West); and OPTIMA, the first European oncology research platform using AI.

The department currently consists of a team of 13 people with complementary profiles: 2 RWD data analysts, 1 RWD biostatistician, 3 RWD data scientists, 1 RWD data manager, 2 RWD data research associates, 1 pharmacy intern, 1 RWD project manager, 1 operations manager, and 1 head of department (pharmacist PU-PH).

Responsibilities

Under the responsibility of the head of the Data Factory & Analytics department, which is part of the ICO's Research and Data Directorate, and in functional liaison with the operations manager, the Data Engineer will play a central role in the management, processing, transformation, exploitation, analysis, and valorization of health data from the ICO's Information System (IS).

Main Activities

The Data Engineer carries out tasks within the Data Factory & Analytics department team and in collaboration with other departments of the Research and Data Directorate (Clinical Research, Translational Research, AI Unit, etc.) as well as the Information Systems Directorate (DSI), the Development and Innovation Directorate (DDI), and the ICO's business and clinical experts:

• ICO Health Data Warehouses (EDS):

  • Actively participate in mapping and mastering the ICO's data assets: knowledge (models) of existing source databases, list tables and fields of interest, in liaison with publishers and application and business referents.
  • Participate in the construction of the EDS in liaison with the DSI and business experts from the Research and Data Directorate:
    • Participate in the development of prerequisites for the ICO's Data IS architecture (governance, repositories, business models).
    • Design the functional architecture of the EDS (integration, quality, security, transformation, persistence, consumption) in liaison with the DSI.
    • Define, with the DSI, the data ingestion processes to be implemented.
    • Automate quality control processes (with orchestrator) and data validation (management of inconsistencies, completeness, format, ...), write qualification reports and associated documentation.
    • Monitor applications over time (configuration, corrective and evolutionary maintenance).
    • Design the technical architecture of the EDS (component selection based on the Research and Data Directorate's constraints).
    • Produce documentation and associated metadata for the EDS (data catalog, specifications, nomenclature, methodological and user guides).
    • Ensure the quality and security of collected data according to current legislative and regulatory obligations.
    • Ensure the integrity and consistency of data from various sources (business applications, external and internal databases).
    • Develop a Key Performance Indicators (KPI) dashboard for the EDS (graphs, time trends, and interactive filters to explore real-world data).

• Other Data Projects: innovation experiments, AI, data exploitation tools

  • Define/clarify needs expressed by business stakeholders.
  • Extract, process, and transform complex data.
  • Design, integrate, and maintain pipelines for exploiting unstructured data using hybrid techniques such as RegEx, NLP, or LLM (Mistral).
  • Contribute with the DSI to defining infrastructure needs with business stakeholders to write specifications.
  • Maintain developments carried out by the team.
  • Ensure documentation associated with developed tools and functionalities.

• Other

  • Be proactive in proposing evolutions of the ICO's IT & Data environments.
  • Ensure technological watch: news, novelties, applications, tools, software, hardware, etc.
  • Other missions may be assigned depending on the level of autonomy and the hospital's current needs.

Profile Sought

Training and Qualifications:

• Master's degree (Bac +5), engineering degree in Data Engineering, data science, or equivalent.
• Minimum 5 years of experience in databases, data engineering, structured and unstructured data warehouses.

Technical Skills:

• Expert in languages: Python, R, SQL.
• Knowledge of database management systems (PostgreSQL, Oracle, MySQL, etc.).
• Good understanding of IT architectures (infrastructure, networks, security).
• Proficiency in relevant tools: e.g., Git, Airflow, Docker, elastic, etc.
• Solid knowledge of health data regulations (GDPR, CNIL, HDS).

Would be a plus:

• Knowledge and use of LLMs.
• Experience in processing medical data and knowledge of data standards (FHIR, OMOP, SNOMED, ICD...).
• Knowledge of data management software (RedCap, Ennov Clinical, ...).
• Notions in oncology (cancer pathologies, terminology, medications).
• Proficiency in written and spoken English.

Personal Skills:

• Rigor and analytical thinking.
• Autonomy, rigor, organizational skills, and respect for deadlines.
• Ability to work in a multidisciplinary team and communicate with non-technical profiles.

Welcome to Institut de Cancérologie de l'Ouest

The Institut de Cancérologie de l'Ouest (ICO) Nantes-Angers is a center of excellence in cancer care and research. Labeled Comprehensive Cancer Center (CCC) by the Organization of European Cancer Institutes (OECI), the ICO is the leading cancer research center in the provinces of France and the third nationally after Institut Gustave Roussy (Villejuif) and Institut Curie (Paris) in terms of patient activity and clinical trial enrollment. Its radiotherapy activity is also the largest in France with 90,000 sessions per year.

For 5 years, the ICO has placed Real-World Data (RWD) and AI at the center of its research and innovation strategy. Its Data Factory & Analytics department is a multidisciplinary, integrated structure dedicated to the collection, qualification, analysis, and valorization of data generated during the care of our patients. The department ensures complete control over the data lifecycle, from its production during patient care within the ICO to its analysis and valorization. It manages the construction, population, and qualification of several data warehouses (EDS), infrastructures, and national programs: the ICO's local EDS, which aims to enable the reuse of RWD for research and organizational activity management; the national CONSORE program (Continuum of Care and Research) in conjunction with the federation of 19 cancer research centers in France (Unicancer); the national EDS OncoDS (Onco Data Share), winner of the Health Data Hub 2023 call for projects dedicated to supporting the creation of hospital EDS; the inter-regional EDS, Ouest Data Hub, in conjunction with the University Hospitals of Rennes, Brest, Nantes, Angers, Tours, and Orléans (GCS HUGO - University Hospitals of the Greater West); and OPTIMA, the first European oncology research platform using AI.

The department currently consists of a team of 13 people with complementary profiles: 2 RWD data analysts, 1 RWD biostatistician, 3 RWD data scientists, 1 RWD data manager, 2 RWD data research associates, 1 pharmacy intern, 1 RWD project manager, 1 operations manager, and 1 head of department (pharmacist PU-PH).

What We Can Offer You

You will benefit from favorable conditions from your arrival:

• Attractive and evolving salary
• Professional experience taken into account (50%) in the calculation of your experience bonus
• Profit-sharing scheme to reward collective commitment

You will develop your skills throughout your career:

• Access to a reinforced training dynamic (supportive care, oncology, patient relations, risk prevention...)
• A training center, HECTOR, to support you in your skill development and professional projects
• Opportunity to get involved in institutional working groups and cross-functional projects

You will evolve in an environment that respects your work-life balance:

• Work organization with paid leave + 16 to 17 RTT days/year (depending on public holidays)
• Specific leave for family events (sick child, moving...)
• Attractive mutual insurance with 75% covered by the employer, options available for you and your family, and quality provident scheme
• Remote work possible 1 day per week on average, after 6 months of seniority

You will enjoy a work environment designed for your well-being:

• Access to CSE benefits: holiday vouchers, cultural/sports subsidies, ticketing...
• Free parking for cars and bikes, 60% contribution to public transport costs
• On-site catering facilities: self-service restaurant, cafeteria, break rooms
• Green mobility bonus (up to €300 gross) for travel by bike, scooter, or carpooling
• Free access to sports sessions upon simple registration
• Company social service to assist you with personal or professional matters (housing, family changes...)

You will be recognized and supported at each stage of your career:

• Possible adjustment of working time at the end of your career, with maintenance of retirement contributions
• A score of 93/100 on the gender equality index, proof of our commitment to equity
• Integration into a center of expertise in care and research, with a regional reach, that supports your professional development.