This is a fully remote position, open to applicants in California.

📋 Description

• Design and engineer scalable data pipelines utilizing AWS Step Functions, Lambda, S3, Textract, and Comprehend

• Create automated workflows for processing documents containing both structured and unstructured data

• Execute document chunking, embeddings, vector indexing, semantic search, and retrieval-augmented generation (RAG) solutions

• Develop and oversee vector databases and knowledge repositories

• Integrate knowledge bases with AI agents to facilitate contextual information retrieval

• Construct and deploy AI agents leveraging the Claude Agent SDK on the Amazon Bedrock AgentCore Runtime

• Establish and maintain CI/CD pipelines using GitHub Actions

• Enhance data pipelines for scalability, security, reliability, and performance

⛳️ Requirements

• Over 12 years of experience in Data Engineering

• AWS certification is mandatory

• Candidates must be located in California

• Strong proficiency in Python and SQL

• Familiarity with AWS Step Functions, Lambda, and S3

• Experience with Amazon Textract and Comprehend

• Understanding of Document AI/OCR technologies

• Background in vector databases and embeddings

• Experience in document chunking and indexing

• Proficiency in advanced retrieval methods and reranking

• Familiarity with RAG and knowledge base integration

• Experience with Amazon Bedrock

• Knowledge of the Claude Agent SDK

• Experience with the AgentCore Runtime

• Proficient in GitHub Actions and CI/CD practices

• Knowledge of AWS IAM and API integrations

• C2C contract engagement

🏝️ Benefits

• Contract duration of over 3 months with the possibility of extension

• Flexible remote or hybrid work arrangement

• Confidential handling of information in accordance with EEO guidelines