Lead Data Scientist – Virtual Models
Job description
Lead Data Scientist role to own a new programme developing virtual pharmacology models from QIMA's biological laboratory data, assessing datasets, building proof-of-concept machine learning models and preparing them for validation and potential commercialisation.
At a glance
- Work mode
- Remote · Europe
- Languages
- English
What you'll do
- Review and assess proposals from QIMA's Business Units
- Examine the underlying data in detail, including its quality, structure, consistency, depth and breadth
- Recommend one or two models with the strongest potential for development, subject to approval by the CEO of QIMA Life Sciences
- Build and manage the required data pipelines
- Clean, structure, integrate and analyse complex biological datasets
- Develop machine learning models and proof of concepts
- Identify data gaps and recommend additional experiments where needed; work with laboratory scientists to help define these experiments, including the required data, measurements and quality criteria
- Establish clear validation criteria and prepare models for independent scientific validation
- Improve the models through repeated testing and iteration
- Ensure that code, data and models are reproducible, traceable and properly documented
- Present results clearly to scientific, technical, commercial and non-specialist audiences
- Support the preparation of a model for future commercialisation, either as a SaaS product or as a service supporting, replacing or complementing wet-lab assays
- Contribute to the documentation and protection of intellectual property related to the models, pipelines and methods
- As the programme grows, may help build and lead a team of additional data scientists
What we're looking for
- PhD in data science, biostatistics, bioinformatics, machine learning or a related field
- 8–10 years of experience in data science, biostatistics and machine learning
- Proven track record of delivering complex machine learning projects using complex biological datasets
- Strong experience building data pipelines, assessing data quality, identifying limitations and defining what additional data is needed
- Experience working with scientists and translating scientific questions into data and modelling approaches
- Excellent communication skills and the ability to explain complex concepts clearly to non-specialists
- A practical, entrepreneurial and hands-on approach
- Ability to work independently and take ownership of an ambiguous, new project
- Strong Python or R skills, including production-quality, version-controlled code
- Experience with cloud data platforms (we use Snowflake) and MLOps practices
Nice to have
- Experience presenting work to clients, partners or other external stakeholders
Apply
Direct apply at QIMA
Opens the job posting at QIMA
About QIMA
QIMA has developed compliance solutions for testing, inspection and certification (TIC) that enable supply chain agility, sustainability and product innovation. Its services are used by 30,000 businesses globally in the consumer products, agri-food and life sciences industries. Through its Life Sciences activities, QIMA develops and delivers scientific testing and research services for its clients.
Mission
Help our clients make products consumers can trust
Key facts
- 6,000+ dedicated Qimates worldwide
- Testing, inspection and certification (TIC)
- Services used by 30,000 businesses globally
- Backed by 6,000+ dedicated Qimates worldwide
- Exceptional Net Promoter Score (NPS) for customer satisfaction
- Launching a new programme to develop virtual pharmacology models
- Laboratories in France, Northern Ireland and Germany