Founding Applied AI Engineer

Matterhaul is building the AI-native operating system for the physical goods supply chain. Distributors and manufacturers run on disconnected systems, manual re-entry, and tribal knowledge that never gets captured. The software that was supposed to fix that never did. We're changing that. Matterhaul sits above the systems these businesses already run — unifying their data, capturing the operational context legacy software misses, and deploying AI agents across quoting, order entry, procurement, dispatch, and customer updates. No rip and replace. Teams go live fast, and Matterhaul expands until it becomes the system the business runs on.

That's the wedge. The vision is bigger: a purpose-built, AI-native platform that doesn't just automate what ERPs do today — it does what they were never capable of.

We're a small team with deep roots in this space. Our founders grew up in the trades and spent careers building products for the physical world at Stripe, Verkada, and Cisco Meraki. We're based in San Francisco's SOMA/Transbay neighborhood, in-office four days a week, and we spend real time with the distributors and operators we build for.

We move fast, ship often, and build for the people who actually do the work.

What You’ll Do

As a Founding Applied AI Enginee you’ll own the AI systems at the core of our product: the sales order extraction and enrichment pipeline, entity resolution engine, product matching and search, and agentic workflows that automate distributor operations. This is a high-autonomy role where you’ll work across the full stack of applied AI—from prompt engineering and eval design to building production ML pipelines.

Your Day to Day:

• Design, build, and iterate on our sales order extraction pipeline—parsing unstructured sales orders (PDFs, emails, EDI) into structured, enriched data
  • Build and maintain entity resolution and product matching systems using a combination of embeddings, full-text search, and knowledge graph lookups
  • Architect agentic loops and multi-step AI workflows (e.g., quote generation, order validation, customer communication) using state machine patterns
  • Design and run evals: build gold datasets, define metrics, run experiments, and use tooling like LangSmith to measure and improve model performance
  • Develop and refine our domain-specific ontology to power structured reasoning over construction products, suppliers, and transactions
  • Integrate and orchestrate LLM calls across the product, including prompt design, output parsing, and fallback handling
  • Collaborate closely with the founding team on product direction and customer feedback loops
  • Fine tune models for specific tasks
  • Build and maintain production observability for our AI pipelines

What We Are Looking For

• 2+ years building production AI/ML systems—not just prototypes, but pipelines that run reliably at scale
• Strong software engineering fundamentals: you write clean, tested, maintainable code
• Deep experience with LLMs in production: prompt engineering, structured extraction, RAG, embeddings, and eval frameworks
• Comfort with TypeScript/Node.js (our stack is Effect.js, Next.js, PostgreSQL)
• Experience with information extraction, NER, entity resolution, or knowledge graphs is a strong plus
• Familiarity with vector databases, search relevance tuning, or ANN algorithms
• You thrive in ambiguity, move fast, and care about shipping things that work for real users

Nice To Have

• Experience in vertical SaaS, B2B, or industry-specific AI applications
• Background in construction, distribution, supply chain, or ERP systems
• Familiarity with RDF/OWL ontologies, PROV-O, or SKOS
• Experience with durable execution patterns or workflow orchestration