Key skills
PythonLLMOpenAIRAGLangChainLangGraphBedrock
About this role
Role Overview
- Collaborate with teams to develop robust Python applications
- Implement and optimize RAG architectures for diverse data
- Engage in document processing and ingestion workflows
- Ensure real-time interfaces via Streaming APIs
- Provide insights through metadata handling and retrieval optimization
- Work on LLM integrations for improved document responses
Requirements
- 5 to 10 years of strong experience in Python development
- Hands-on experience with RAG (Retrieval Augmented Generation) architectures
- Experience working with Vector Databases (embeddings, similarity search, indexing)
- Good understanding of MCP (Model Context Protocol) or similar agent integration patterns
- Experience in Document Parsing & Extraction (PDF, structured/unstructured data)
- Building Document Ingestion Pipelines (loading → parsing → chunking → embedding → storage)
- Experience with Streaming APIs and SSE (Server-Sent Events) for real-time responses
- Implementation of Document Citation / Source Attribution in LLM responses
- Familiarity with LLM integrations (OpenAI / Bedrock / similar)
- Experience handling metadata, indexing, and retrieval optimization
- Experience with LangChain / LangGraph or similar frameworks (Good to Have)
- Experience with chat/agent-based UI integrations (Good to Have)
Tech Stack
- Python