RAG Architect - Remote

We are seeking an experienced RAG Architect to design and lead scalable Retrieval-Augmented Generation (RAG) solutions using enterprise data, LLMs, vector search, and AI orchestration technologies.
Key Responsibilities
Design end-to-end RAG architecture for enterprise AI applications.
Architect document ingestion, chunking, embedding, indexing, retrieval, and generation pipelines.
Design and optimize vector search and semantic retrieval solutions.
Integrate LLMs, embedding models, vector databases, and enterprise data sources.
Implement advanced retrieval techniques including hybrid search, reranking, metadata filtering, and query optimization.
Design RAG solutions using frameworks such as LangChain, LangGraph, LlamaIndex, or equivalent.
Establish RAG evaluation frameworks for relevance, accuracy, groundedness, hallucination, and retrieval quality.
Implement security, access control, PII protection, guardrails, and responsible AI practices.
Design scalable APIs and microservices for production RAG applications.
Collaborate with Data Engineering, ML Engineering, Cloud, Security, and Application teams.
Lead technical design, architecture reviews, POCs, and production implementation.
Required Skills
8+ years of software/AI engineering experience with strong architecture experience.
Strong hands-on experience with RAG and LLM-based applications.
Expertise in Python, LLMs, embeddings, prompt engineering, and NLP.
Strong knowledge of Vector Databases such as Pinecone, Weaviate, Milvus, pgvector, or OpenSearch.
Experience with LangChain, LangGraph, LlamaIndex, or similar frameworks.
Strong understanding of semantic search, hybrid search, reranking, chunking, embeddings, and retrieval optimization.
Experience with AWS, Azure, or GCP AI/cloud services.
Experience designing REST APIs, microservices, and scalable AI platforms.
Knowledge of Docker, Kubernetes, CI/CD, and MLOps.
Strong understanding of AI security, data privacy, RBAC, and LLM guardrails.
Preferred Skills
Experience with Agentic AI / AI Agents.
Knowledge of Graph RAG / Knowledge Graphs.
Experience with multimodal RAG.
Experience with AWS Bedrock, Azure OpenAI, or Google Vertex AI.
Experience with RAG evaluation and observability platforms.
Experience building enterprise-grade GenAI platforms.