Join Cruise Planners to design, build, and run production-grade data and AI systems that power analytics, advisor-facing experiences, and internal automation. This hybrid role in Coral Springs, FL blends AWS data engineering with applied generative AI on Amazon Bedrock, including retrieval-augmented generation and agent development using the Strands Agents SDK.
What you’ll build
You’ll create reliable pipelines and data models that feed a Redshift data warehouse, then extend those capabilities into AI workflows that turn unstructured inputs into structured outputs and searchable knowledge. You’ll also develop and operate agentic systems and LLM-based data products that support reporting, search, and automated operations.
Responsibilities
- Design and operate AWS data pipelines using Glue, Step Functions, Lambda, EventBridge, and S3 to deliver data into Redshift.
- Stand up and run containerized production pipelines on AWS Fargate / ECS, including scheduled ingest or scrape, enrichment, and delivery, with CloudWatch alarms and health monitoring.
- Design dimensional data models (facts, conformed dimensions, and analytics marts) in Redshift using a zero-ETL replica of the operational source.
- Implement document-extraction pipelines using Amazon Bedrock Data Automation blueprints, delivering structured results to downstream consumers via webhooks or queues.
- Build and operate Bedrock Knowledge Bases for retrieval-augmented generation, including source preparation, indexing, retrieval evaluation, and cost or latency tuning.
- Build agents on Bedrock AgentCore using the Strands Agents SDK, including supervisor or sub-agent topologies, tool definitions, and deployment hardening.
- Create applied-LLM data products for reporting, search, and agentic operations.
- Deploy and operate AWS services end to end, including internal web apps and demos.
- Develop internal tooling and integrations, including MCP servers.
- Prototype and ship new AI-powered applications for advisors and internal teams.
- Maintain operational quality through logs, alarms, runbooks, on-call response, and post-incident documentation, while continuously monitoring quality and data-privacy compliance.
- Carry out day-to-day development using Claude Code with project-scoped MCP servers, documenting decisions and architectures in the team wiki.
Requirements
- Bachelor’s degree in Computer Science, Data Science, Statistics, Engineering, or a related field.
- Master’s preferred at the Senior level.
- Relevant production experience scaled to the role level (Data & AI Engineer I / II / Senior).
- Authorization to work in the United States without sponsorship.
Career level expectations
- Data & AI Engineer I: Executes scoped work end to end under guidance; ships well-defined pipelines, blueprints, or Knowledge Base load jobs.
- Data & AI Engineer II: Owns workstreams end to end (design, build, deploy, operate) and makes architecture choices within an established pattern; writes the playbook a peer can ship from.
- Senior Data & AI Engineer: Owns multi-system architecture; establishes new patterns (for example, AgentCore deployment or multi-agent topology) without precedent; coaches peers; represents the team in cross-functional design, operating across the full stack including production Fargate pipelines, inbound AWS deployments, applied-LLM data products, and end-to-end agent architecture.
Technologies: AWS, Glue, Redshift, Step Functions, Lambda, S3, EventBridge, AWS Fargate, ECS, CloudWatch, Amazon Bedrock, Data Automation, Knowledge Bases, AgentCore, Strands Agents SDK, Claude Code, MCP servers, Python, SQL, Infrastructure-as-code
