Backend Engineer – Ruby on Rails, PostgreSQL & LLM Pipelines

About the role

This backend position focuses on data‑intensive product testing and compliance. You will deepen existing Rails pipelines, improve messy external data ingestion, and make structured results actionable for customers.

Key responsibilities

• Improve and rework the PDF extraction pipeline using document AI and LLM extraction.
• Strengthen validation and correction layers to ensure compliance‑grade accuracy.
• Build a taxonomy for unit normalization, naming conventions, method equivalence, and detection limits across labs.
• Enable cohort analysis across suppliers, products, and categories once data is harmonized.
• Organize and query test results for trends, out‑of‑spec risk, and variance by batch.
• Guarantee statistical defensibility of data presented to customers.
• Design agentic workflows that are auditable and verifiable.
• Develop data models that serve multiple audiences (customers, ops, partners, compliance) without forking.

Required profile

• 4+ years experience as a backend engineer with strong Ruby on Rails and PostgreSQL expertise.
• Proven ability to design robust, adaptable data models.
• Experience building ingestion pipelines from unstructured external sources.
• Strong analytical rigor to assess data quality for compliance decisions.
• Comfort working with LLM/agentic APIs in production.
• Familiarity with analytical data stores such as ClickHouse (BigQuery, Snowflake, DuckDB) is a plus.
• Excellent communication and autonomous work style in a fast‑moving startup.

Required skills

• Ruby on Rails
• PostgreSQL
• ClickHouse
• Claude API
• Reducto (document parsing)
• Turbo (Hotwire)
• Tailwind CSS
• LLM APIs