Related skills
python computer vision rag llm ocrπ Description
- Design, train, and optimize models to extract structured data from documents.
- Build end-to-end ML systems: datasets, training, inference, deployment.
- Drive production AI features powering PandaDoc's document workflows.
- Tackle robustness, latency, observability, and RAG quality in production.
- Experiment with frontier and open-source models and vision language systems.
- Collaborate with product, engineering, and design to translate requirements.
π― Requirements
- 5+ years of Python experience.
- Experience training, fine-tuning, and deploying CV models for document intelligence.
- Hands-on with document understanding frameworks (LayoutLM, Donut, DocFormer) and OCR.
- Deploying and optimizing models with vLLM, TGI, TensorRT, or ONNX Runtime.
- LLMs for document intelligence workflows (frontier and open-source).
- Spatial reasoning for form field detection and absolute positioning.
π Benefits
- Honest, open culture with feedback and growth.
- Work from anywhere β distributed worldwide.
- 6 self-care days.
- And much more!
Meet JobCopilot: Your Personal AI Job Hunter
Automatically Apply to Engineering Jobs. Just set your
preferences and Job Copilot will do the rest β finding, filtering, and applying while you focus on what matters.
Help us maintain the quality of jobs posted on Empllo!
Is this position not a remote job?
Let us know!