About this role
Lead computer vision efforts at STACK to improve detection and segmentation systems for construction documents. You'll own end-to-end pipelines from model training through production serving, working with messy real-world PDFs and drawings to deliver geometrically accurate, reliable predictions.
Must have
5+ years experience building production computer vision systems for detection, segmentation, or structured geometry extraction
Experience with messy real-world image data or large unstructured visual datasets
Strong understanding of detection and segmentation tradeoffs including architecture and training data design
Ability to measure system performance with evaluation, testing, and production metrics
Experience with multimodal models including vision-language models and document AI systems
Understanding of grounding linking model outputs to source data or coordinates
Backend engineering experience with APIs, async processing, and scalable GPU services
Technologies
Responsibilities
Design, build, and improve end-to-end detection and segmentation pipelines for document images
Improve document ingestion for PDFs and unstructured files including parsing and rendering
Increase model accuracy, boundary quality, and reliability of predictions for downstream use
Integrate modern detection and segmentation models into production workflows
Build post-processing that turns model output into structured usable geometry
Define evaluation metrics, investigate failure cases, and drive continuous quality improvements
Optimize latency, reliability, and cost across the inference and post-processing stack
Own training infrastructure, dataset curation, annotation quality, and improvement loops
Benefits
Recruitment process
Remote-first async-friendly environment with focus on ownership and deep work
Not a model-training-only role; you'll own data, training, post-processing, and serving
Not a research-only role; emphasis on production-grade systems
Company values radical honesty, customer obsession, moving with purpose, and growing together
Equal opportunity employer committed to diversity and inclusion
Role eligible for health insurance, life insurance, 401k, and paid time off
Final salary determined by qualifications, experience, skillset, and geographic location
Similar offers
Research Scientist, Generalist Embodied Agent Research - PhD New College Grad 20
168,000 – 304,750 USD
/ year
AI and FSI Developer Technology Engineer - New College Grad 2026
124,000 – 195,500 USD
/ year
Sr. Security Engineer I - Enterprise Security
135,482 – 227,700 USD
/ year
Senior GPU Raytracing Engineer
184,000 – 356,500 USD
/ year
Staff Software Engineer
170,000 – 190,000 USD
/ year