AI Engineer

Delve Deeper is a performance media agency focused on the charity and nonprofit sector, partnering with organizations that invest $5M–$20M annually in media. They deliver advanced analytics, intent-based audience segmentation, full-service media management, and personalized creative for data-driven growth. The company has been recognized as Built In Colorado's “Best Places to Work” for five consecutive years.

• 4+ years in software, data engineering, ML, or AI platform work with production system ownership.
• Experience with media platform APIs such as Google Ads, Meta, DV360, Semrush, SerpAPI.
• Strong production-grade skills in Python and SQL.
• Experience with MCP or equivalent integration layers.
• Hands-on experience building or operating LLM applications, agentic systems, or tool-calling workflows.
• Knowledge of workflow orchestration tools: Airflow, Dagster, Prefect, dbt.
• ETL/ELT pipeline design with emphasis on data reliability, schema management, and contract enforcement.
• Cloud infrastructure experience with AWS, GCP, or Azure and containerized deployments using Docker.
• Experience defining evaluation frameworks and success criteria for model outputs.
• Slack API and webhook-based workflow automation expertise.
• Familiarity with vector databases and RAG patterns for long-context data retrieval.
• Experience shipping systems mixing model logic, deterministic business rules, and human approval flows.
• Experience with LLM evaluation tooling including token cost tracking, hallucination detection, and model benchmarking.

• Build, iterate, and maintain AI agents within the architecture defined by the Lead AI Engineer, including prompt design, tool wiring, context routing, failure handling, and output validation.
• Integrate data components across media platforms by ingesting, normalizing to schema, and routing to correct agent context while monitoring schema drift.
• Develop with defined success criteria and regression tests, run prompt benchmarking, and proactively flag hallucination patterns or regressions.
• Build and maintain ETL/ELT pipelines to support automated callouts and optimization reporting, ensuring data freshness and reliability.
• Operate within and extend the MCP connector library for external platform APIs handling rate limits, retries, and failure modes.
• Build and maintain Slack-based human-in-the-loop approval workflows, feedback capture, exception alerts, and notifications.
• Monitor output quality of agents in production, respond to incidents, and drive root-cause fixes, alerting Lead AI Engineer on scope or complexity affecting delivery.

EU BASED ONLY!