Related skills
pytorch langchain langgraph clip pymupdf📋 Description
- Build pipelines to extract data from visual docs using Vision-Language Models.
- Orchestrate data to the app logic with LangChain/LangGraph.
- Handle PDF processing with PyMuPDF and layout parsing.
- Craft prompts and control flows to avoid hallucinations.
- Optimize cost and performance in vision/orchestration layers.
🎯 Requirements
- LLM orchestration with LangChain/LangGraph
- Vision models: GPT-4V, Claude 3.5
- Document intelligence: Donut, Pix2Struct, Unstructured.io
- PDF extraction: PyMuPDF, pdfplumber
- Python ML stack: PyTorch or TensorFlow
- Nice-to-have: fine-tuning vision/lang models
🎁 Benefits
- Put People First: caring, open culture
- Imagine Better: optimistic and proactive
- Expect Excellence: strive for best
- One Able. Many Voices: diverse and inclusive
Meet JobCopilot: Your Personal AI Job Hunter
Automatically Apply to Engineering Jobs. Just set your
preferences and Job Copilot will do the rest — 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!