Description

Key Skills: MGCP, Vector Database Integration, Python, Retrieval-Augmented Generation, Lang graph, LangChain Development

Roles and Responsibilities:

• Develop RAG architectures in Python including embeddings, similarity search, indexing, and retrieval optimization.
• Build document parsing and extraction workflows for PDFs and structured/unstructured data sources.
• Implement document ingestion pipelines covering loading, parsing, chunking, embedding, and storage with strong metadata handling.
• Integrate MCP (Model Context Protocol) or similar agent integration frameworks to support context-aware LLM behavior.
• Build Streaming APIs using SSE (Server-Sent Events) to deliver real-time AI responses.
• Implement document citation and source attribution capabilities within LLM-generated responses.
• Ensure reliable indexing, metadata management, and traceability for high-quality AI outputs.
• Collaborate with cross-functional engineering and product teams to design scalable AI-driven solutions.
• Optimize application performance, scalability, reliability, and retrieval accuracy.
• Write clean, maintainable, reusable, and production-ready Python code following engineering best practices.
• Participate in code reviews, architecture discussions, troubleshooting, and continuous improvement initiatives.

Skills Required:

• Strong experience in Python application development and backend engineering.
• Expertise in Retrieval Augmented Generation (RAG) architectures and workflows.
• Hands-on experience with vector databases, embeddings, similarity search, and retrieval optimization.
• Experience building document parsing and extraction workflows for structured and unstructured data sources.
• Strong understanding of document ingestion pipelines including loading, chunking, embedding, indexing, and storage.
• Knowledge of LLM integration patterns and context-aware AI application development.
• Experience implementing MCP (Model Context Protocol) or similar agent/context integration frameworks.
• Expertise in building Streaming APIs using SSE (Server-Sent Events) for real-time AI responses.
• Ability to implement source attribution, metadata-driven indexing, and traceability mechanisms in LLM systems.
• Strong understanding of scalable backend architecture, API development, and asynchronous processing.
• Experience troubleshooting AI pipelines, retrieval workflows, and indexing performance issues.
• Strong analytical, debugging, and problem-solving skills.

Nice to Have

• Experience with LangChain and LangGraph frameworks.
• Exposure to chat-based and agent-based UI integrations.
• Familiarity with conversational AI application architectures and orchestration frameworks.

Education: Bachelor's degree in Computer Science or equivalent.

• Master's degree in Computer Science is preferred

Key Skills

Education

Any Graduate