Regulatory Data Specialist

O projekcie:
About GFcomply
GFcomply is a SaaS platform delivering compliance and labelling solutions for the food industry. Our Data Team collects, structures and maintains regulatory data from official sources worldwide — the trusted foundation that powers the compliance and labelling services our customers rely on.

The team runs an automated ETL (Extract/ Transform/ Load) pipeline built around Claude AI, turning regulations from many geographies, languages and frameworks into a structured, searchable database. As a Regulatory Data Specialist you will be a core operator of that pipeline and a growing contributor to its improvement.
The role
You will make sure GFcomply’s compliance database accurately reflects the latest food regulations across every covered geography. You will run structured data-collection sessions through the ETL pipeline, review and validate the outputs, keep our ontology aligned, and help improve the pipeline and its supporting tools over time.

This is a mixed role — roughly 60% operational (running sessions, validating data, managing exceptions) and 40% contributory (refining prompts, improving processes, flagging issues to the team). It is a junior position with a clear path to grow.

Wymagania:
Who we’re looking for?
We expect solid fundamentals at hire and will support you to grow into the rest. You will likely recognise yourself in most of the following.
- You are comfortable reading official regulatory or technical texts and translating them into structured data.- You have a meticulous, zero-error mindset — accuracy matters more to you than speed.- You are methodical and consistent: you can follow a multi-step process reliably, session after session.- You are curious about AI tools and confident using Claude through structured prompts to do real work.- You have strong written English; additional languages (French, German, Spanish, Portuguese, Arabic, Chinese, …) are a real plus given our source documents.- You hold a degree or equivalent experience in food science, food law, nutrition, regulatory affairs, life sciences, data, or a related field - must have.

What you’ll work with

- AI platform: Claude (Anthropic) — the core pipeline tool for all extraction and alignment steps.- Data files: Excel / CSV — regulation URLs, schemas, reference files and session outputs.- Sources: EUR-Lex, FDA, FSA, ANVISA, GSO, Health Canada, GB Standards, Codex and others.- Geographies: EU, USA, UK, Codex, Brazil, GCC, Canada, Mercosur, China and supplement-specific countries (expanding).- Topics: food additives, contaminants, labelling & claims, novel foods, allergens (expanding).- Collaboration: direct work with the Data Team and occasional contact with our regulatory partners.

Codzienne zadania:
- What you’ll do day to day (operational):
- Run each pipeline session end to end: scope → extract → align → validate → load.
- Validate the accuracy and traceability of every row you process, resolving exceptions as they arise.
- Keep regulatory data in GFcomply current and correct as sources change.
- Align substances and product categories to the GFcomply ontology, flagging new entities for review.
- Ongoing (contributory)
- Improve AI instructions, prompts and procedures that make sessions faster and more reliable.
- Participate in team retrospectives on session quality and help test pipeline updates.
- Surface friction and edge cases early, and propose practical improvements.