Senior AI Engineer – Generative AI & Data Platform (AWS)

Job Title: Senior AI Engineer – Generative AI & Data Platform (AWS) Location Irvine, CA (Hybrid) Work Schedule: 4 days onsite per week (3 days in Irvine office, 1 day in Downtown Los Angeles office, 1 day remote) Role Summary We are seeking an experienced Senior AI Engineer to design, build, and scale enterprise-grade Generative AI solutions on AWS. This role focuses on developing production-ready AI platforms that leverage Large Language Models (LLMs), Retrieval-Augmented Generation (RAG), vector search, knowledge graphs, and agentic AI frameworks. The ideal candidate will have strong expertise in AI platform engineering, backend development, cloud-native architectures, and large-scale data processing. You will work closely with cross-functional teams to deliver secure, scalable, and high-performing AI capabilities for customer-facing applications. Key Responsibilities Generative AI & LLM Engineering • Design, develop, and deploy production-grade Generative AI applications using RAG architectures. • Build embedding generation pipelines and semantic search solutions. • Develop prompt engineering, prompt orchestration, and evaluation frameworks. • Implement vector search using Amazon OpenSearch or similar vector databases. • Build knowledge graph solutions using Amazon Neptune. • Develop agentic AI workflows using LangGraph, AutoGen, CrewAI, or similar frameworks. • Integrate LangChain or LlamaIndex for retrieval orchestration, tool calling, and context management. • Evaluate LLM performance based on accuracy, latency, cost, and response quality. AI Platform & Data Engineering • Design scalable data ingestion and transformation pipelines using Databricks and Apache Spark. • Develop document processing pipelines including parsing, chunking, metadata enrichment, and embedding generation. • Maintain high standards for data quality, governance, lineage, and auditability. • Implement data access controls and retention policies.