Machine Learning Engineer

We're looking for a Machine Learning Engineer to train custom models using our internal data. This work spans design generation, cost estimation, evaluating the complexity and difficulty of a given design, and extracting structured data out of existing documentation. We're looking for someone who has trained custom models on large, parameter-rich datasets, ideally with a geometric or spatial component, and who is energized by problems in that space specifically.

To conform to U.S. Government export regulations, applicant must be a (i) U.S. citizen or national, (ii) U.S. lawful, permanent resident (aka green card holder), (iii) Refugee under 8 U.S.C. § 1157, or (iv) Asylee under 8 U.S.C. § 1158, or be eligible to obtain the required authorizations from the U.S. Department of State.

Learn more about the ITAR here .

• Train and iterate on custom ML models using Layup's internal manufacturing and design data

• Build models that estimate cost and predict design complexity or manufacturing difficulty from part geometry

• Develop models that generate or assist in generating new designs based on historical design data

• Build pipelines to extract structured data (specs, dimensions, material callouts, etc.) from existing engineering documents and drawings

• Evaluate and select modeling approaches suited to geometric, spatial, and other structured data, rather than text-based problems

• Work closely with engineering and manufacturing teams to source, clean, and label internal datasets

• Own model performance end-to-end, from data pipeline through training, evaluation, and deployment into internal tools

• Continuously identify new opportunities where custom models could improve design, estimation, or manufacturing workflows
• Experience training custom models beyond basic labeling or fine-tuning workflows

• Experience with advanced object detection at minimum; data classification experience is a strong plus

• Experience with geometry-based modeling is highly preferred

• Strongest fit is someone whose background is in structured, spatial, or geometric data problems rather than natural language or LLM-centric work
• Experience training geometry-specific models