Python Developer

Project Work Format:

• Remote work from home (office setup possible upon request)
• Project documentation in Confluence
• Task management in Jira

Main Tasks:

• Develop and maintain backend services and data pipelines using Python 3 (functions, classes, context managers, modules, dependency management).
• Work within virtual environments using venv, Poetry, or Pipenv.
• Build and integrate AI/NLP solutions with OpenAI API, Hugging Face Transformers, LangChain, or LlamaIndex.
• Implement and optimize RAG (Retrieval-Augmented Generation) systems, including embedding generation, tokenization, and similarity search.
• Work with vector databases such as Pinecone, FAISS, Chroma, Weaviate, or Qdrant for embedding storage and retrieval.
• Create and maintain API wrappers and backend services using FastAPI or Flask.
• Design and execute ETL pipelines, including:
  
  • Data extraction from sources such as Google Drive, Notion, and Shopify API.
  • Text cleaning (HTML stripping, stopword removal, normalization).
  • Data storage in structured databases or vector stores.
  • Model calls for automated Q&A and content generation.
• Manage configuration and environment variables using dotenv.
• Containerize and deploy services with Docker.
• Deploy and maintain applications on Render, Railway, Hugging Face Spaces, or with a basic understanding of AWS.
• Work with data formats such as JSON, CSV, and YAML.
• Conduct code reviews and ensure adherence to best coding practices.

What We Expect from a Candidate:

• Strong proficiency in Python 3 and its ecosystem.
• Experience with virtual environments (venv, Poetry, or Pipenv).
• Knowledge of REST / GraphQL APIs and experience integrating with external services using requests or httpx.
• Proficiency in data handling (JSON, CSV, YAML).
• Familiarity with LangChain concepts: retriever, LLM, prompt template, memory, chain, tool.
• Experience with at least one vector database (Pinecone, FAISS, Chroma, Weaviate, Qdrant).
• Understanding of tokenization, embeddings, and similarity search principles
• Ability to write clean, maintainable, and well-documented code following best practices.

Will Be a Plus:

• Familiarity with Streamlit, Gradio, or Next.js + FastAPI for building user interfaces.
• Understanding of RAG architecture and data retrieval workflows.
• Experience with ETL pipelines and text preprocessing.
• Knowledge of Docker Compose and CI/CD processes.
• Basic understanding of AWS services for deployment and storage.
• Technical English proficiency sufficient for reading and understanding documentation.

Example Technology Stack:

• Python 3.10+
• LangChain — model chaining and integrations
• OpenAI API — embeddings and responses
• Hugging Face Transformers — NLP models
• LlamaIndex — document indexing and retrieval
• ChromaDB / Pinecone / FAISS / Weaviate / Qdrant — vector databases
• FastAPI / Flask — backend API frameworks
• Docker — containerization and deployment
• dotenv — configuration management
• Render / Railway / Hugging Face Spaces / AWS (basic) — deployment platforms
• Streamlit / Gradio / Next.js — optional UI layer
• Poetry / Pipenv / venv — environment managemen
• JSON / CSV / YAML — data formats