Data and ML Engineer

• Own end-to-end data extraction pipelines, converting unstructured inputs (e.g., emails, PDFs, specifications, and supporting documents) into validated, structured datasets.
• Architect and evolve the core data model and infrastructure that unifies entities such as suppliers, documents, requests, pricing, and certifications.
• Design and implement new data processing modules that integrate into an event-driven pipeline.
• Build evaluation frameworks, regression testing, and monitoring to drive extraction accuracy above 85%+ while systematically addressing edge cases.
• Identify opportunities to enhance data granularity, aggregation, and quality to support downstream product features.
• Collaborate closely with product, sales, and customer teams to align the data layer with real business needs and priorities.
• Leverage ML models, agents, and automation to scale extraction processes efficiently rather than relying on manual effort.

• 7+ years of experience building production data systems, with a strong track record of architecting and owning data infrastructure from scratch at early-stage or growth companies.
• Demonstrated ability to design broad system architecture and end-to-end pipelines, not just incremental features.
• Deep expertise working with complex, messy, unstructured data sources and turning them into reliable structured outputs.
• Experience treating extraction challenges as ML problems - including building eval sets, performance tracking, and iterative improvements.
• Proficiency in data modeling, pipeline orchestration, and integrating with modern backend systems (e.g., Node/TypeScript environments).
• Bonus: Background in document extraction, NLP, ML pipelines, or supply chain/procurement-related domains

Compensation Package: 200-220k, equity