Job Summary
We are seeking a seasoned LLM Engineer to spearhead the development of an end-to-end drawing-diff engine, leveraging multimodal technology to provide robust change-impact narratives.
This is a key opportunity for an accomplished professional with a proven track record in computer vision and document AI, looking to drive innovation and deliver scalable solutions in a collaborative environment.
Key Responsibilities
- Lead the design and implementation of a version-aware diff pipeline for architectural / structural drawings.
- Develop and train detectors & segmenters for symbols, title blocks, and revision clouds; achieve production-grade mAP / F1.
- Implement geometry-aware post-processing to reduce false positives.
Document Understanding
Engineer OCR + layout models to read legends, notes, schedules, and BOM tables; normalize to structured JSON.Build version-aware entity tracking across revisions.GeoAI & LLM / RAG
Design retrieval over drawings / specs with reranking; ground LLM answers in evidence with citations and clickable locations.Generate change-impact summaries with rules + LLM verification; measure factual precision.Productization & DevOps
Ship microservices, batch & streaming workers, GPU inference, and observability.Own evaluation : dataset curation, data labeling guidelines, ablation / A-B tests, and regression suites.Requirements
5+ years of production Python (3.x) building ML-heavy backends; strong PyTorch.3+ years in computer vision for detection / segmentation / OCR or document AI at scale.Hands-on with multimodal LLM / RAG, vector DBs, and rerankers.Proven experience parsing engineering drawings or complex PDFs, including geometry and layout reasoning.Solid MLOps : reproducible training, CI / CD, model packaging, monitoring; cloud on AWS / GCP.Fluent written & spoken English.