Chemistry Data Scientist/Material Informatics Engineer

Company Description:

DigAIT is a scientific technology and consulting partner that helps organizations in the chemical and life sciences industries accelerate digital transformation. The team integrates AI, IT, scientific data, and domain expertise to modernize processes across research, development, laboratories, manufacturing, and operations. DigAIT’s capabilities span process modeling, digital process transformation, laboratory and manufacturing solutions, data analytics, business intelligence, cheminformatics, bioinformatics, and advanced AI, including LLMs and generative models. The company supports clients from process assessment and future-state design through implementation, data integration, analytics, and AI adoption, leveraging platforms such as SAP Signavio, LIMS, ELN, MES, ERP, Power BI, Tableau, AWS, Azure, Python, and modern AI/LLM tools. DigAIT’s mission is to make scientific processes more connected, intelligent, data-driven, and scalable for its global partners.

Role Description:

We are looking for an experienced freelance consultant with expertise in cheminformatics, data science, and R&D digitalization to support the scale of machine learning capabilities within the enterprise R&D data management platform used for chemical research and formulation development by our Client. The consultant will work closely with our Client's digitalization and scientific teams to improve R&D data quality, develop and optimize scientific workflows, assess advanced analytics capabilities, and identify opportunities to enhance the platform’s value for R&D users.

Key responsibilities

• Machine Learning Capability Assessment
• Evaluate the platform’s existing machine learning and advanced analytics capabilities.
• Develop and execute representative use cases relevant to formulation and synthesis R&D.
• Assess functionality, usability, scalability, and technical limitations.
• Identify gaps and opportunities for enhancement.
• Translate findings into a prioritized product backlog, clearly linking proposed enhancements to business value and R&D use cases.

2. Scientific Data Visualization & Analytics

• Assess existing data visualization, dashboarding, and reporting capabilities within the platform.
• Develop representative dashboards and scientific visualizations for R&D users.
• Identify usability gaps, missing analytical capabilities, and additional reporting requirements.
• Recommend improvements that enhance data interpretation and decision-making.
• Prioritize visualization and analytics enhancements based on business impact and user needs.

3. Data Quality Monitoring & Governance

• Design and implement automated data quality monitoring solutions for master data and ELN transactional data.
• Define and implement data quality rules covering completeness, consistency, validity, uniqueness, and integrity.
• Develop dashboards and KPIs to continuously monitor data quality across R&D processes.
• Identify recurring data quality issues and recommend corrective and preventive measures.
• Recommend improvements to data governance, standards, and processes to increase data reliability, consistency, and usability.

4. Machine Learning Model Development & Platform Benchmarking

• Recreate representative ML use cases independently in Python and compare their performance with the models/capabilities available within the ELN platform.
• Assess differences in model performance, data preparation, feature handling, usability, and scalability.
• Identify situations where the ELN platform performs well and where external/custom models provide better results.
• Train, validate, and optimize models using suitable ML algorithms.
• Work with the digitalization/IT team to integrate selected Python-based models into the ELN or R&D data platform through appropriate APIs or services.

5. Cheminformatics Workflow Development

• Develop and implement cheminformatics workflows for calculating, enriching, and managing molecular, chemical, and ingredient properties.
• Generate molecular descriptors, fingerprints, structures, and other chemical representations using industry-standard cheminformatics libraries.
• Integrate computed chemical properties into the R&D data management platform to support analytics, reporting, and machine learning use cases.
• Ensure workflows are reusable, scalable, and aligned with scientific and business requirements

Qualifications

• PhD in Chemistry, Chemical Engineering, Materials Science, Cheminformatics, or a related scientific discipline, with a strong focus on data science, machine learning, or scientific informatics.
• 5+ years of relevant professional experience with a PhD or a Postdoc, preferably in chemical R&D, formulation, cheminformatics, materials informatics, or R&D digitalization.
• Strong understanding of chemistry formulations (Synthesis, application related recipe development) with expertise to derive features from complex formulation data, augment additional features based on raw materials of the formulations (eg., using chemi-informatics)
• Strong expertise in data science, data analysis, and statistical modeling, with the ability to translate scientific and business questions into robust analytical and machine learning workflows.
• Hands-on experience developing and validating machine learning models in Python, including model benchmarking, performance evaluation, feature engineering, and model optimization.
• Experience working with experimental, formulation, synthesis, master, and transactional R&D data, including data cleaning, validation, transformation, and integration.
• Strong programming skills in Python and/or R, with experience developing reusable data processing, automation, and ETL workflows using REST APIs.
• Practical experience with cheminformatics or materials informatics libraries, such as RDKit, ASE, scikit-learn, or equivalent tools, including molecular descriptors, fingerprints, chemical representations, or material properties.
• Experience developing and evaluating scientific data visualizations, dashboards, and analytical reports to support R&D decision-making.
• Strong communication and documentation skills, with the ability to explain complex scientific and technical concepts to both technical and non-technical stakeholders.