Job Details

Job Summary:

• Develop pipelines to parse documents, chunk, vectorise, and store vector data.
• Design schemas for vector stores to optimise retrieval efficiency.
• Create prompt templates using advanced prompt engineering techniques.
• Implement few-shot prompting strategies for improved LLM interactions.
• Develop semantic agents and interfaces for seamless agent collaboration.
• Build microservices and expose them as APIs for scalable solutions.
• Work closely with architects and full-stack developers to deliver AI solutions.
• pply best practices for data management and model deployment.
• Ensure scalability and performance of generative AI applications.

• Designed and developed scalable generative AI platforms for enterprise use cases.
• Built end-to-end pipelines for document parsing, chunking, vectorisation, and storage in vector databases like FAISS, Pinecone, and Chroma.
• Created and optimised vector store schemas for efficient semantic retrieval.
• Developed prompt templates using few-shot and zero-shot prompting techniques.
• Engineered semantic agents and built interfaces for agent collaboration in LLM workflows.
• Built and deployed microservices exposing LLM capabilities through scalable APIs.