Key Responsibilities
- Adapt and extend existing document processing pipelines
- Implement feature extraction logic for different document and project types
- Develop and tune prompts for reliable data extraction
- Build and maintain Python modules supporting AI workflows
- Support integration of extracted data into downstream models and frontend views
Required Skills
- Solid Python development experience
- Practical experience with LLMs and document processing use cases
- Understanding of embeddings, vector search, and feature extraction
- Familiarity with LangChain or similar tools
- Comfort working in fast-moving, early-stage environments
Nice to Have
- Experience with Weaviate, Supabase, or similar platforms
- Exposure to DevOps workflows
This role is remote first, hybrid later in HCMC.
