Andela
|AI Engineering Fellow
Remote, , US
Summary
Building production-grade AI applications with a focus on scalability and latency optimization, leveraging Python and OpenAI APIs to develop advanced RAG systems and structured prompt pipelines.
Highlights
Built production-grade AI applications using Python and OpenAI APIs, focusing on scalability and latency optimization for high-performance systems.
Developed robust RAG (Retrieval-Augmented Generation) systems, including document chunking, vector embeddings, and semantic search pipelines.
Designed and evaluated structured prompt pipelines, ensuring reliable LLM output generation for critical applications.
Applied AI system design trade-offs, including latency, cost, and scaling considerations, to optimize solutions for production-oriented scenarios.