Chemical Data Scientist

Valdera•San Francisco, CA

25d•Remote

About The Position

Valdera is seeking a Chemical Data Scientist to build and maintain the data pipelines that ensure the accuracy, currency, and structure of Valdera's supplier and chemical product data. This role is foundational to the company's procurement platform, impacting the reliability of matches between buyers and suppliers. The position requires strong data engineering fundamentals and a working knowledge of chemical industry data to manage and standardize diverse data sources into a cohesive product database. The Chemical Data Scientist will own the entire data pipeline, from data collection to the application of models for data cleaning, matching, and classification. This role involves collaborating with Supplier Management and Engineering to address data gaps and ensure the accuracy that buyers and suppliers depend on.

Requirements

5+ years of experience in a data science, data engineering, or applied data role, ideally with exposure to messy, real-world or industrial datasets
Working knowledge of chemistry or chemical industry data — comfort with CAS numbers, chemical properties, SDS documents, NAICS classification, and supplier certifications
Strong Python skills, with experience building web scrapers and data pipelines
Experience with data cleaning and normalization at scale, and a good eye for spotting inconsistencies in unstructured data
Familiarity with building or applying matching, deduplication, or classification models (traditional ML or LLM-based approaches)
Hands-on experience using AI tools and LLMs to accelerate data extraction, enrichment, or engineering workflows
Startup mindset with a strong sense of ownership — comfortable working independently in a fast-moving, remote environment with ambiguous, evolving priorities

Responsibilities

Design and build pipelines to collect supplier data and chemical product information (specifications, CAS numbers, certifications, SDS/regulatory documents, NAICS classification of manufacturing plants) from supplier sites, distributor catalogs, trade databases, and other public and semi-structured sources
Develop and maintain web scrapers and automated ETL workflows to keep supplier and product data current at scale
Clean, normalize, and reconcile inconsistent supplier data into structured, standardized formats suitable for internal tools and analytics
Apply chemical domain knowledge to validate and enrich data — resolving product names, CAS numbers, synonyms, and specifications across suppliers
Evaluate and improve matching and classification models to map suppliers and products to buyer requirements, and to identify overlapping or equivalent chemical offerings
Partner with Supplier Management and Engineering to define data quality standards, identify gaps in supplier coverage, and prioritize new data sources
Own pipeline health and data quality, and drive the KPIs that measure overall data coverage