Senior Applied Data Scientist
il y a 1 jour
Lyon
About the Company Inpart is the leading provider of partnering technology solutions for the biopharma industry. More than 60% of the world's largest pharma companies and 100+ innovative biotech’s rely on Inpart's platform to manage their partnerships. With complementary data and event offerings, Inpart delivers structure, process, efficiency, security, and compliance to more than 160 clients. Inpart's team is diverse and international. Offices in four cities and three countries bring together more than 150 employees from more than 35 nations driven by core values of care, diversity, and excellence. About the Role We are looking for a highly capable Data Scientist to design, test, and productionise high-value data processing capabilities for our customer-facing data products. This role will work with complex customer and third-party datasets to build algorithms and logic for harmonisation, deduplication, entity resolution, ontology mapping, data quality improvement, and enriched data outputs. This is a hands-on technical role requiring strong analytical judgement, rigorous scientific thinking, and practical engineering discipline. You will be expected to deeply understand messy real-world data, develop robust approaches, benchmark results continuously, and turn successful methods into reliable, documented, reproducible workflows that can be used in production. Responsibilities • Analyse raw, ingested data from multiple heterogeneous sources to understand structure, quality, distributions, anomalies, and product value, • Design and implement algorithms for data harmonisation, deduplication, entity resolution, ontology mapping, classification, enrichment, and data quality improvement, • Define transformation rules, business logic, validation checks, and data contracts that produce consistent, well-structured datasets across sources, • Build clean, tested, reproducible workflows for transformation, validation, benchmarking, and model development, • Apply a rigorous experimental approach, including continuous testing, benchmarking, evaluation metrics, and regression monitoring of data outputs, • Work closely with data engineers, product managers, and downstream consumers to align on schemas, formats, quality expectations, SLAs, and delivery requirements, • Shape downstream data outputs for use in products, APIs, analytical datasets, reports, and customer-facing integrations, • Clearly document transformation logic, assumptions, caveats, data lineage, evaluation results, and known limitations Qualifications • Formal education in data science, computer science, statistics, mathematics, engineering, or a related quantitative discipline, or equivalent hands-on professional experience, • Significant professional experience in data science, applied machine learning, data engineering, analytics engineering, or algorithmic data processing, • Strong hands-on experience with Python, SQL, Git, testing, reproducible development workflows, and working with complex structured or semi-structured datasets, • Demonstrable experience designing and evaluating algorithms for entity resolution, deduplication, matching, classification, clustering, harmonization, ontology mapping, or data enrichment, • Demonstrable experience productionising data science, machine learning, or algorithmic workflows across services, pipelines, APIs, or data products, • Demonstrable experience working with customers, commercial, scientific, healthcare, pharma, life sciences, or other complex domain-specific datasets would be highly valuable Required Skills • A strong applied data scientist who can turn complex, messy datasets into reliable product capabilities, • Excellent Python and SQL skills, with the ability to write production-quality, testable, maintainable code, • Strong experience with data normalisation, harmonisation, entity matching, deduplication, classification, ontology mapping, or similar data processing challenges, • Experience delivering customer-facing production systems where reliability, security, scalability, and maintainability are important, • A rigorous, evidence-led approach to development, including experimentation, benchmarking, validation, and measurable quality improvement, • Strong analytical judgement, with the ability to spot data quality issues, edge cases, outliers, conflicting values, and unexpected behavioural changes, • Someone who can work across data engineering, product, and technical stakeholders to turn ambiguous data problems into practical, deliverable solutions Preferred Skills • Experience with machine learning frameworks and libraries, • Familiarity with cloud platforms and data storage solutions Equal Opportunity Statement As part of our equal opportunities policy, we strongly encourage all qualified individuals to apply for the advertised position, regardless of origin, gender, sexual orientation, gender identity, religion, age, disability or any other legally protected status. We firmly believe in the value of diversity and inclusion in our workplace, and are committed to providing equitable opportunities for all our employees, from the recruitment process through to professional development. As such, we ensure that our selection criteria are strictly based on the skills, experience and qualifications required to perform the duties of the job.