Scientific Data Architect - Biologics Manufacturing & Quality Control

Description

The company is a scientific data and AI business building an operating system for scientific intelligence. It helps large life sciences firms turn scattered scientific data into AI-ready assets and workflows that speed up discovery, development and manufacturing. Its partners include NVIDIA, Databricks, Thermo Fisher Scientific, Snowflake, Google and Microsoft.

This role supports a partnership with a top 25 global biopharma manufacturing and quality organization. You will design the scientific data models and use cases that link manufacturing steps, lab results and product quality across sites and external partners, supporting investigations, continued process verification (CPV), process improvement, technology transfer and AI for biologics manufacturing.

As part of interviews, candidates are asked to read 'The Tetra Way', a document written by the CEO, and to judge whether its mission, culture and expectations suit them.

Apply even if you do not meet every qualification. Strong candidates often do not.

Responsibilities

• Lead onsite discovery with manufacturing, MSAT, QC, IT and Quality teams, alongside the Scientific Business Analyst. Map workflows, examine representative source data, find gaps, and set prioritised use cases with measurable outcomes and acceptance criteria.
• With the platform knowledge engineering team, build product, process and QC data models for biologics manufacturing. Create shared structures and controlled vocabularies that still respect product, modality and site needs.
• Model batch and material genealogy, including splits, pools, intermediate lots, and links between drug substance and drug product. Tie process measurements and QC results to the right batch, unit operation, sample, method version and specification.
• Map data across sites and external manufacturing partners, reconciling identifiers, terms, units, timestamps and process hierarchies while keeping source provenance.
• Create use cases for investigation evidence, CPV, cross-batch comparison, yield and process analysis, and technology transfer. Turn scientific questions into data requirements, calculations, prototypes and production specifications.
• Write Python parsers, transformations, quality checks and applications on the platform, working with engineers to deliver reliable, maintainable data products.
• Prepare contextualised datasets for statistical, mechanistic and AI/ML models. Work with scientists and applied AI engineers to judge data fit, interpret outputs and assess performance.
• Support verification and validation with documented requirements, source-to-target mappings, test evidence and reproducible analyses, within the partner's Quality processes.
• Demonstrate solutions regularly, act on user feedback, and train partner teams to maintain and extend what you deliver.
• Harmonise multi-site manufacturing data and integrate external CMO/CDMO data. Work with process historian and time-series data, chromatography data, statistical process monitoring and multivariate analysis. Use Databricks, cloud data platforms, and ICH, ISA-88 and ISA-95 information models.

Requirements

• You bring deep biologics manufacturing and QC experience, plus the technical skill to design, prototype and build scientific data solutions. You understand how manufacturing generates data, how QC labs test product quality, and how to keep the links between those records intact.
• You work well with manufacturing scientists, MSAT, manufacturing IT, QC, Quality Assurance, data engineers and product teams. You turn their questions into explicit data requirements, reusable models and tools they use daily.
• You own work from first site discovery through build and adoption. You write code, check source data, test assumptions with scientific users and show working solutions.
• You have a minimum of 3-5 years of direct biologic drug manufacturing and QC experience, including substantial work with monoclonal antibodies or other recombinant therapeutic proteins. You have designed data models and delivered analytical or digital use cases from manufacturing and QC data for these modalities.
• You have strong Python and SQL skills, and have built parsers, transformations, APIs and analytical applications over tabular and JSON data.
• You can explain architecture decisions and scientific findings to lab users, manufacturing teams, engineers and business leaders.
• Desired: relevant life sciences experience, with substantial work in biologics manufacturing, process development, MSAT, analytical development or QC.
• Desired: a clear grasp of upstream and downstream biologics operations (cell culture, harvest, chromatography, filtration and drug substance production), and how process conditions affect yield and quality.
• Desired: experience defining or delivering manufacturing or QC use cases such as batch investigations, CPV, yield analysis, raw-material variability assessment, stability trending or technology transfer.
• Desired: experience delivering in GxP settings, covering traceability, data integrity, controlled change, reproducible calculations and work with Quality and Validation teams.
• Desired: a track record designing conceptual, logical and physical data models that link products, batches, material lots, process steps, equipment, samples, analytical results and quality events across systems.
• Desired: experience integrating data from LIMS, laboratory instruments, process historians, MES, ERP, ELN and quality management systems.

Conditions

Travel up to 50% of working time between partner manufacturing sites for discovery, implementation, workshops, training and adoption support.

Visa sponsorship is not currently offered for this position.

Benefits

• Employer pays 100% of benefit costs for eligible employees and immediate family members.
• Unlimited paid time off.
• 401K plan.
• Company-paid life insurance and LTD/STD coverage.
• A culture of continuous improvement, with career growth and coaching.
• Target base salary range of $140,000 - $240,000. Final pay depends on the candidate's specific experience, localised market data and internal team equity.