Senior AI Engineer
of modern LLM patterns: embeddings, vector databases, prompt engineering, RAG, agentic systems, and evaluation Experience...
of modern LLM patterns: embeddings, vector databases, prompt engineering, RAG, agentic systems, and evaluation Experience...
vector, developing recommendation to eliminate vulnerability/weakness. Provide guidance on active Plans of Action...
of vector databases — chunking strategies, retrieval tuning, reranking, citation handling, and context-window management. Build... tooling and patterns — model registries, deployment pipelines, GitOps, lineage, and rollback. Vector databases and RAG: Hands...
and inference cost management. RAG architecture knowledge- vector databases, embedding models, and retrieval strategies. B...
AI system design. Deep knowledge of LLMs, vector databases, and orchestration frameworks (LangChain, LangGraph, LlamaIndex...
. Track and evaluate emerging AI infrastructure (Azure AI Foundry, foundation models, vector and semantic search, MCP...
. In this role, you will design and optimize next-generation search and retrieval experiences using Elasticsearch, Vector Search..., including lexical, semantic, and vector-based search techniques. Apply Retrieval-Augmented Generation (RAG) patterns to enhance...
, financial services, or public sector. Depth in one or more of: RAG at scale, fine-tuning / LoRA, vector search tuning, multi...
, including SQL and NoSQL databases, as well as modern data architectures Familiarity with vector-based and graph-based data...
with optimized chunking, reranking, grounding, and hybrid/vector retrieval using OpenSearch and pgvector. Apply Guardrails and data... models. Deep understanding of RAG design, hybrid/vector search (OpenSearch, pgvector), grounding, and citation techniques...