Senior AI Engineer (GenAI and Data Platform - AWS)

Role: Senior AI Engineer (GenAI + Data Platform AWS) Location: 4 days a week onsite is must (3 days in Irvine, CA & 1 Day in Downtown, LA, CA) Job Type: Contract Role Summary We are seeking a Senior AI Engineer to design, build, and scale a production‑grade Generative AI and Data Platform on AWS. The role focuses on enabling LLM‑powered capabilities through vector search, graph‑based knowledge systems, and governed data pipelines. Must Have Skills Generative AI / LLM (RAG, embeddings, prompt engineering) AWS Cloud (OpenSearch, Neptune, DynamoDB, ElastiCache/Redis) Vector Search & Retrieval Systems (OpenSearch / vector DB) Graph Databases (Amazon Neptune, knowledge graphs) LLM Frameworks (LangChain / LlamaIndex) Agentic AI Frameworks (LangGraph / AutoGen / CrewAI) Databricks & Apache Spark (data pipelines, embedding pipelines) Backend/API Development (Python, scalable APIs, microservices) Must Have Certifications AWS Certified Solutions Architect AWS Certified Machine Learning Specialty AWS Data Engineer Certification Ideal Candidate Responsibilities Own end‑to‑end delivery across the AI lifecycle, including data ingestion and knowledge curation, embeddings and retrieval systems, backend services and APIs, CI/CD pipelines and deployment. Build and operationalize LLM‑powered applications using Retrieval‑Augmented Generation (RAG), embeddings pipelines, prompt orchestration and evaluation frameworks, vector search systems (Amazon OpenSearch), graph‑based knowledge systems (Amazon Neptune). Integrate supporting infrastructure: Amazon ElastiCache (Redis) for session state and caching, DynamoDB for scalable, low‑latency data access. Implement agentic workflows using LangGraph, AutoGen, CrewAI (or equivalent). Integrate with LLM frameworks: LangChain, LlamaIndex (tool calling, retrieval orchestration, context management). Define standards for tool integration and context‑sharing patterns (MCP‑style designs). Evaluate LLM models and retrieval strategies across latency, cost, accuracy, and context limitations. Design and build scalable data pipelines using Databricks and Apache Spark; handle data ingestion, transformation, document processing (chunking, metadata tagging), embedding generation and indexing. Ensure high data quality standards: validation, completeness, consistency, monitoring. Implement data governance frameworks: data classification and access controls, retention policies, auditability and lineage tracking. Develop backend services exposing AI capabilities through secure, scalable APIs; define best practices for API contracts, reliability (retry logic, circuit breakers, idempotency), and reusability across teams. Deploy production systems using Docker (containerization) and Kubernetes (orchestration); build and manage CI/CD pipelines for AI and data workloads. Implement deployment strategies: blue/green deployments, canary releases, rollback strategies, feature flags. Ensure system reliability: monitoring (latency, failures, cost, data freshness), alerting and observability, secrets management, least‑privilege access; optimize platform performance and cost. Define and track GenAI quality metrics: grounding/faithfulness, retrieval relevance, response consistency, latency and cost per request. Implement prompt/version tracking, offline evaluation pipelines, continuous improvement workflows. Implement secure AI systems: access control and authentication, data protection policies, responsible AI guardrails. Ensure compliance with best practices in AI safety, data privacy, monitoring and auditability. Qualifications Bachelor's or Master's degree in Computer Science, Data Science, AI or related field. Proven experience building production‑grade AI platforms and systems. Strong background in end‑to‑end AI/ML lifecycle delivery. #J-18808-Ljbffr