LLM-focused Python Dev for Prototype Build
Budget: €18 – €36 EUR
Python Developer (LLM / AI Data Processing) for Prototype Development
Description:
We are looking to develop a system that can analyze, structure, and connect text data with a Large Language Model (LLM).
We’re seeking an experienced Python developer with strong LLM expertise to build an initial functional concept (prototype).
⸻
Responsibilities:
• Build a pipeline to transform unstructured text data into structured formats (e.g., JSON, YAML).
• Integrate these structured data sets with a Large Language Model (LLM) via LangChain or LlamaIndex.
• Develop a simple chat interface (e.g., using Streamlit or Gradio).
• Implement data storage and retrieval through a database or vector database (e.g., Chroma, FAISS, Pinecone).
• Conduct testing and documentation of the workflow.
⸻
Requirements:
• Strong proficiency in Python.
• Hands-on experience with LangChain or LlamaIndex.
• Experience using OpenAI API or similar LLM frameworks.
• Understanding of Retrieval-Augmented Generation (RAG) concepts.
• Solid grasp of JSON data structures and database handling.
• Good command of English and clear communication skills.
⸻
Project Details:
• Start: Immediately
• Duration: 4–8 weeks (Goal: functional prototype)
• Compensation: To be discussed (hourly or project-based)
Further details about the specific use case will be shared after signing a Non-Disclosure Agreement (NDA).
Description:
We are looking to develop a system that can analyze, structure, and connect text data with a Large Language Model (LLM).
We’re seeking an experienced Python developer with strong LLM expertise to build an initial functional concept (prototype).
⸻
Responsibilities:
• Build a pipeline to transform unstructured text data into structured formats (e.g., JSON, YAML).
• Integrate these structured data sets with a Large Language Model (LLM) via LangChain or LlamaIndex.
• Develop a simple chat interface (e.g., using Streamlit or Gradio).
• Implement data storage and retrieval through a database or vector database (e.g., Chroma, FAISS, Pinecone).
• Conduct testing and documentation of the workflow.
⸻
Requirements:
• Strong proficiency in Python.
• Hands-on experience with LangChain or LlamaIndex.
• Experience using OpenAI API or similar LLM frameworks.
• Understanding of Retrieval-Augmented Generation (RAG) concepts.
• Solid grasp of JSON data structures and database handling.
• Good command of English and clear communication skills.
⸻
Project Details:
• Start: Immediately
• Duration: 4–8 weeks (Goal: functional prototype)
• Compensation: To be discussed (hourly or project-based)
Further details about the specific use case will be shared after signing a Non-Disclosure Agreement (NDA).