AI Engineer

Job Description

Job Description

AI Engineer
Onsite 
Minneapolis MN

·     Role spans AI engineering

·      Tech decisions influenced by broader product stack:

o        Frontend/backend for RAG and app work: Next.js and NestJS (Node)

o        Light work with data pipelines: Python; Snowflake as the data platform (medallion architecture: bronze/silver/gold)

·         Tools and AI coding assistants:

o        Claude Code

o        GitHub Copilot via Visual Studio

o        Evaluating vendor AI tools (e.g., Snowflake AI, Domo AI); use-case dependent.

o        MCP servers: discussed; on roadmap; not currently required for internal LLM routing/abstraction.

Must Have Requirements

·       Strong Python experience (production-grade software engineering).

·        Hands-on experience working with LLMs in production (general LLM best practices; not strictly RAG). Examples:

o        Efficient interaction patterns with LLMs (token management, sending full articles vs. selective context)

o        Agentic approaches for complex reasoning (e.g., applying AP style guide across thousands of rules)

o        Practical strategies to avoid context overload and maintain relevance.

·                  Ability to “run with projects,” operate independently, and collaborate with stakeholders.

·                  Minimum experience: approximately 5 years; must have “done it before.”

Should Have

·                  Familiarity with Next.js/NestJS/Node for application/RAG-related work; strong Python candidates can ramp with AI coding tools.

·                  CI/CD experience; Terraform not required (team strength exists, can learn on the job).

·                  Good culture fit: collaborative, mission-driven, able to navigate flexible stack choices aligned with product teams.

Could Have:

·          Exposure to data engineering concepts and tooling:

o        Building ingestion/ETL/ELT pipelines (Python)

o        Working with Snowflake; experience in similar platforms (Redshift, Synapse) acceptable with ability to translate principles.

o        Familiarity with medallion architecture and data modeling concepts is helpful but not strictly required (team can support ramp-up).

Additional Notes

·                  RAG work currently lives in Next/Nest (Node); none in Python at present.

·                  Preference for principles over specific vendor experience; candidates with adjacent platform knowledge can adapt.