Prototyping Architect, PACE, AWS Prototyping and AI Customer Engineering (PACE)
agents, multi-agent systems, RAG architectures, and LLM-powered applications that demonstrate a clear path to production...
agents, multi-agent systems, RAG architectures, and LLM-powered applications that demonstrate a clear path to production...
— embeddings and vector search (k-NN indexes for RAG). Amazon DocumentDB — conversation/session storage (MongoDB-compatible schema... — OpenSearch k-NN, dimension tuning, index optimization for RAG. Kubernetes (EKS) for ML workloads — GPU node pools, autoscaling...
AI copilots, chatbots, document intelligence solutions, and recommendation systems. Implement Retrieval Augmented Generation (RAG.... Proven experience with LLMs and foundation models in an enterprise context. Strong knowledge of RAG architectures and vector...
& agenda's. Ensure the project remains on track, all tasks completed within deadline. Keep the RAG Status updated accurate...
to translate evolving EQS needs into scalable solutions. This could include designing a RAG-enabled assistant to support reporting... such as machine learning models, LLMs, RAG architectures, and prompt engineering. Beyond technical capability, you bring...
Core Skills AI/GenAI development (LLMs, AI agents, RAG, automation) Strong software engineering (Python, APIs...
) Production AI systems and observability challenges (prompting, context windows, RAG, hallucinations, provider variability..., LlamaIndex), RAG/vector search concepts, and enterprise integration considerations. Experience with DevOps/Platform Engineering...
. Identify opportunities to apply technologies such as large language models (LLMs), retrieval-augmented generation (RAG...
with AI orchestration (AI Core, APIs, external models) Understanding of RAG, LLM integration or conversational UX Hands-on experience...
and influence technical decisions Hands-on experience building AI agents (e.g., using LangChain or LlamaIndex), implementing RAG...