onsite
AI Data Scientist
AI Data Scientist
This role involves designing and implementing context engineering and RAG strategies for LLM-based solutions. Key responsibilities include optimizing chunking approaches, developing embedding pipelines, and building retrieval pipelines using frameworks like LlamaIndex, while also managing data lakes and ensuring data governance.
About the role
Responsibilities
- Design and implement context engineering and RAG strategies for LLM-based solutions.
- Develop and optimize chunking approaches, embedding pipelines, and semantic retrieval models.
- Build and maintain retrieval pipelines using frameworks such as LlamaIndex.
- Design and operate enterprise data lakes using Microsoft Fabric / OneLake.
- Prepare, curate, and enrich data for AI consumption, including unstructured enterprise content.
- Ensure data governance, security, and Responsible AI compliance in collaboration with governance and security teams.
- Support AI solutions for Microsoft Azure AI and Amazon AWS Bedrock.
- Document best practices and support knowledge sharing within the AI and IT teams.
Skills
LlmRagLlamaindexMicrosoft FabricOneLakeMicrosoft Azure AIAmazon AWS Bedrock