Sr & Jr AWS AI/Data Engineers
Position#1Job Title: Senior AWS AI / Data EngineerLocation: Detroit, MI Hire Type: Long-term contract Experience: 7+ years | Detroit, MI (mandatory) — Remote up to 50% travel | Agentic AI LLMs Python AWS Native Data Pipelines Structured + Unstructured Data ABOUT THE ROLEAs a Senior AWS AI/Data Engineer at DataFactZ you will architect and deliver enterprise-grade AI and data pipeline solutions for large-scale client engagements. You will lead the design of agentic AI systems, LLM-powered applications, and high-throughput data pipelines on AWS — translating complex business problems into production-ready solutions while mentoring junior engineers. KEY RESPONSIBILITIES• Design and build end-to-end data pipelines for ingesting, transforming, and serving structured (SQL, Redshift, Parquet) and unstructured (PDFs, emails, documents, images) data on AWS• Architect agentic AI systems using LLMs with tool use, memory, and multi-step reasoning via Amazon Bedrock, OpenAI, or Anthropic Claude• Build multi-agent orchestration workflows using LangChain, LlamaIndex, CrewAI, or AutoGen for enterprise automation• Design RAG pipelines connecting structured and unstructured data sources to LLMs via vector databases (Pinecone, OpenSearch, pgvector)• Lead AWS data architecture across S3, Glue, Lambda, EMR, Athena, Step Functions, and Redshift• Develop prompt engineering strategies and fine-tuning approaches for domain-specific LLM customization• Mentor junior engineers, lead code reviews, and drive engineering best practices• Engage client stakeholders to scope AI/data use cases, define success metrics, and deliver on commitments REQUIRED SKILLS• Python: Advanced proficiency for data engineering, pipeline orchestration, and AI integrations• AWS services: Deep hands-on experience with S3, Glue, Lambda, EMR, Athena, Step Functions, Redshift, and Bedrock• LLMs & Agentic AI: Production experience building LLM-powered agents, tool-calling workflows, and multi-agent systems• Data pipelines: Batch and real-time ETL/ELT for large-scale structured and unstructured datasets• RAG & vector search: Building retrieval-augmented generation systems with embedding pipelines and semantic search• System design: Architecting scalable, secure, cost-efficient cloud-native data and AI systems• Leadership: Proven ability to lead technical workstreams and communicate designs to senior stakeholders PREFERRED• AWS certifications: Solutions Architect, Data Analytics, or Machine Learning Specialty• Document intelligence: AWS Textract or custom document parsing pipelines• Multi-modal AI: Experience with vision or document-aware models