Sr. Data Engineer (GenAI & AWS) Remote/Hybrid with Travel
About The Position
The Senior Data Engineer will design, build, and maintain AWS-based data pipelines and AI-powered document-processing workflows. The role focuses on extracting, transforming, and processing structured and unstructured data; implementing document chunking, embeddings, vector indexing, and semantic search; and supporting Retrieval-Augmented Generation (RAG) through vector databases and knowledge bases. The engineer will integrate knowledge bases with AI agents and may build and deploy agents using the Claude Agent SDK on Amazon Bedrock AgentCore Runtime. The position is remote or hybrid and requires residence in a western time zone to provide time-zone coverage. The engineer must be comfortable traveling to client sites for workshops and meetings. Python is the primary language. Overall experience is listed as 12–20+ years.
Requirements
- 12–20+ years of overall experience.
- Python and SQL.
- AWS Step Functions, Lambda, and S3.
- Amazon Textract and Comprehend.
- Vector databases and embeddings.
- Document chunking and indexing.
- RAG and knowledge-base integration.
- Amazon Bedrock.
- GitHub Actions CI/CD.
- AWS IAM and API integrations.
- Located in a western time zone.
- Comfortable traveling to client sites for workshops and meetings.
Nice To Haves
- TypeScript.
- AWS Glue.
- Document AI / OCR.
- OpenSearch, Pinecone, or pgvector.
- Advanced retrieval and reranking.
- LangChain or LlamaIndex.
- Terraform or AWS CDK.
- Claude Agent SDK and AgentCore Runtime are listed as good-to-have unless the individual must personally build and deploy the Claude agents; in that case, they are must-have skills.
Responsibilities
- Design and develop data pipelines using AWS Step Functions, Lambda, S3, Textract, and Comprehend.
- Build automated document-processing workflows to extract, transform, and process structured and unstructured data.
- Implement document chunking, embeddings, vector indexing, and semantic search.
- Develop and maintain vector databases and knowledge bases to support RAG.
- Integrate knowledge bases with AI agents for contextual information retrieval.
- Build AI agents using the Claude Agent SDK and deploy them on Amazon Bedrock AgentCore Runtime, if personally responsible for agent development and deployment.
- Develop CI/CD pipelines using GitHub Actions to automate builds, testing, and deployments.
- Optimize data pipelines for scalability, reliability, security, and performance.
- Travel to client sites for workshops and meetings.
Stand Out From the Crowd
Upload your resume and get instant feedback on how well it matches this job.
What This Job Offers
Job Type
Full-time
Career Level
Senior
Education Level
No Education Listed
