ML Engineer

About Trunk Tools

Trunk Tools is a leading AI company revolutionizing construction, the second-largest industry on earth. Founded by builders and technologists from Stanford and MIT, the company has raised $70M in total funding from top-tier investors including Insight Partners, Redpoint, and Innovation Endeavors.

The company's software is used by over 140,000 field professionals, impacting millions of users and contributing to $10B+ in built projects. With 65+ employees including 25+ engineers, the team is scaling rapidly and entering a period of hypergrowth.

Mission

Build the future of construction through intelligent automation by embedding AI directly into field operations, transforming a $13+ trillion industry that still largely runs on analog processes.

What You Will Do

• Own and evolve core parts of the AI platform, spanning search, retrieval, and multi-agent orchestration
• Lead the design and build-out of a multi-agent system, including defining new agent "pillars" and how they collaborate in production
• Architect and scale document processing pipelines (Kubernetes-based), including ingestion, parsing, chunking, indexing, and structured data extraction across heterogeneous document types
• Design and iterate on search and retrieval systems (ranking, query understanding, QA) grounded in real user behavior and product needs
• Help build and expand the knowledge graph, modeling entities and relationships to power downstream reasoning and retrieval
• Drive ambiguous, high-impact projects end-to-end, from problem definition through experimentation and productionization
• Establish and improve evaluation and experimentation frameworks to measure system quality and guide iteration
• Write clean, maintainable, production-grade code and raise the bar for engineering quality across the team

Who You Are

• 7+ years of experience building and shipping production ML/AI systems
• Proven track record of leading complex, ambiguous projects and driving them to impact
• Strong experience with agentic systems, LLM-based applications, or orchestration frameworks
• Deep experience in document processing pipelines (e.g., parsing, chunking, indexing, structured extraction), ideally in distributed systems (Kubernetes or similar)
• Experience building or working with knowledge graphs / provenance graphs and modeling relationships between entities
• Background in search/retrieval, ranking, or related areas