AI Data Engineer

Candidates should demonstrate hands-on engineering and coding experience, not just architectural or conceptual exposure.

1. Strong Python and scripting skills, with demonstrated production-level coding experience.
2. Hands-on Data Engineering experience, including building and supporting scalable data pipelines and data processing solutions.
3. Practical experience with technologies relevant to the role, including AWS Glue, AWS DMS, Apache Kafka, Apache Airflow, and/or Snowflake.
4. Strong hands-on experience with AWS services and cloud-native data engineering.
5. Demonstrated experience using Claude Code, Kiro, or equivalent AI-assisted development tools for actual software engineering and coding.
6. Ability to translate business and technical requirements into clear engineering specifications, technical designs, and acceptance criteria.
7. Ability to review, validate, debug, test, and optimize AI-generated code, rather than relying on generated output without engineering validation.
8. Hands-on experience developing AWS Lambda functions using Python, including integration with other AWS services.

Strongly Preferred:

• Hands-on experience with Kiro, particularly specification-driven development.
• Practical experience using Claude Code for software/data engineering.
• Experience with Model Context Protocol (MCP) and MCP-based integrations.
• Working knowledge of TypeScript.
• Relevant AWS certification, such as AWS Certified Data Engineer, Developer, or Solutions Architect.
• Experience implementing automated testing, CI/CD pipelines, code-quality controls, and deployment automation.
• Understanding of Agentic AI engineering concepts, including agents, tools, context, memory, workflow orchestration, and human-in-the-loop patterns.

Key Differentiators: Candidates will stand out if they have practical experience with:

• Strands Agents SDK or comparable agent-development frameworks/SDKs.
• Designing and building MCP servers, tools, and integrations.
• Creating reusable Kiro steering rules, specifications, development patterns, and engineering standards.
• Building agentic workflows and tool orchestration, particularly where AI agents interact with AWS services, data platforms, APIs, and enterprise systems.
• Applying AI-assisted engineering throughout the SDLC, from requirements/specification * code generation * review/testing * deployment and operational support.