Data Engineer

As we grow, we are seeking a Data Engineer to play a crucial part in driving our research and development efforts forward. As a Data Engineer you will be part of the new team building the infrastructure that underpins and acts as the critical bridge between raw chemical data and our machine learning models. Your main focus will be to build the pipeline infrastructure and tooling for data ingestion, moving towards self-serve setup for the scientific team members. You'll also be responsible for securing, collecting, cleaning, standardising, and tagging diverse chemical datasets to create high-quality training data for our ML researchers while working closely with our chemistry team to ensure scientific accuracy.

What You Will Do

Data Pipeline Development

• Design and build robust data pipelines for materials science datasets, experimental results, and computational chemistry outputs.

• Develop processes to integrate diverse data sources including materials databases, literature, patent filings, and laboratory instruments.

• Create automated workflows for processing crystallographic data, molecular structures, and materials properties (you don’t need to have direct domain experience - we can help bring you up to speed!).

• Build scalable systems to handle high-throughput computational chemistry calculations and experimental data.

Data Quality & Standardisation

• Partner closely with the scientific and research teams to implement automated quality checks for crystal structure data, chemical compositions, and experimental measurements.

• Create standardisation protocols for materials nomenclature, units, and measurement conditions.

• Build monitoring systems to ensure data integrity across all pipelines.

Collaboration & Integration

• You will also be working hand in hand with ML researchers to understand data requirements for model training and inference.

• Partner with materials scientists to ensure accurate representation of domain knowledge in data schemas.

• Integrate with laboratory automation systems and computational chemistry software.

• Support real-time data needs for AI-driven materials discovery experiments.

Must Have Skills and Qualifications

• You are someone who gets excited about the opportunity to enable scientists to work on world changing challenges in this domain, with a personal interest in the potential applications of the technology that Cusp is building.

• You’re a builder of tools and infrastructure who enjoys making life as easy as possible for the teams, providing self-serve, reliable and scalable ingestion pipelines.

• You have at least 3+ years experience in data engineering roles, preferably in scientific or research environments - you would be joining as a data engineering subject matter expert who can not only work autonomously but also provide guidance on best practice.

• High level of proficiency in Python and databases with experience in large-scale data processing - as part of our engineering team you’ll be programming regularly, not just scripting.

• You’re an advanced user of workflow orchestration tools (e.g. Airflow, Prefect, Dagster, Flyte or similar).

• Solid experience with containerisation (Docker, Kubernetes) and CI/CD practices.

• You have direct experience handling large/complex datasets and are interested in working with scientific packages.

• You’re a fast learner when it comes to new tools/systems.

• You enjoy (and have experience in) designing systems that scale with growing.