Conduct technical discovery and architecture reviews to understand current usage, identify gaps, and propose best-practice architectures that increase adoption, performance, security, and cost efficiency.
Data Engineering and Integration: Build the data and knowledge pipelines required for AI use cases, with a focus on reliable ingestion, preparation, retrieval, and access-control-aware use of information.
Data Engineering and Integration: Build the data and knowledge pipelines required for AI use cases, with a focus on reliable ingestion, preparation, retrieval, and access-control-aware use of information.
Design and implement RAG pipelines and LLM application workflows (prompting, retrieval, tool calling, agents), and expose them as reliable, scalable services.
Managing critical interfaces and project lifecycles: Coordinating with internal teams and external stakeholders (consultants, contractors, operators) to resolve technical gaps while maintaining a sharp focus on safety, risk management, and long-term efficiency.