Description

Key Skills: LLM, Retrieval-Augmented Generation, Python, Vector Database Integration, Function Calling (OpenAI/Anthropic), Vector

Roles and Responsibilities:

• Design and implement RAG architectures for LLM-based question answering and knowledge retrieval.
• Build document ingestion pipelines (loading, parsing, chunking, embedding, and storage) with metadata handling.
• Integrate vector databases to support embeddings, similarity search, indexing, and retrieval optimization.
• Implement streaming APIs using SSE (Server-Sent Events) for real-time LLM responses.
• Enable document citation and source attribution in LLM outputs.
• Work with LLM integrations (OpenAI / Bedrock / similar) and agent integration patterns such as MCP (Model Context Protocol).
• Optimize indexing and retrieval performance for accurate and fast responses.

Skills Required:

• Strong hands-on experience in Python development.
• Experience building Retrieval-Augmented Generation (RAG) applications.
• Good understanding of LLM integrations and AI application development.
• Experience with vector databases, embeddings, and similarity search concepts.
• Knowledge of document ingestion, parsing, indexing, and retrieval pipelines.
• Familiarity with streaming APIs and SSE (Server-Sent Events).
• Understanding of metadata handling and source attribution in AI systems.
• Exposure to MCP (Model Context Protocol), LangChain, or LangGraph is preferred.
• Familiarity with OpenAI, Anthropic, Bedrock, or similar AI platforms is an advantage.
• Strong problem-solving and performance optimization skills.

Education: Bachelor's Degree in related field

Key Skills

Education

Any Graduate