Experience 5+ years in software engineering/data science, with 2+ years focused on LLMs.
Core Focus Core LLM Implementation, RAG Architecture, Prompt Engineering, and Model Integration.
Key Responsibilities LLM Implementation: Design and implement core business logic and APIs using Python to integrate with the Azure OpenAI Service.
RAG System Development: Build and optimize Retrieval-Augmented Generation (RAG) pipelines, leveraging Azure AI Search, vector databases, and Azure storage to ground models with proprietary data.
Prompt Engineering: Develop and maintain complex, dynamic prompts for both chat and other generative tasks, focusing on maximizing model accuracy and reducing hallucinations.
Model Evaluation: Implement evaluation frameworks and metrics to continuously test and improve the performance of Generative AI models in pre-production and production. Required Skills Expert proficiency in Python and experience with relevant LLM orchestration libraries (e.g., LangChain).
Deep practical experience with Azure OpenAI Service deployment and configuration.
Proven ability to design and implement RAG architectures on the Azure platform.
Solid understanding of NLP, semantic search, and prompt engineering techniques.
