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. The agency specializes in advanced analytics, intent-based audience segmentation, full-service media management, and personalized creative, delivering a data-driven approach to growth for mission-driven teams.

• 4+ years of experience in software, data engineering, ML, or AI platform work with production system ownership.
• Experience with media platform APIs including Google Ads, Meta, DV360, Semrush, and 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.
• Proficiency with workflow orchestration tools such as Airflow, Dagster, Prefect, dbt.
• ETL/ELT pipeline design and ensuring data reliability in production, including schema management and freshness monitoring.
• Knowledge of cloud infrastructure: AWS, GCP, or Azure; and containerized deployments using Docker.
• Experience defining evaluation frameworks and success criteria for model outputs.
• Experience with Slack API and webhook-based workflow automation.
• Familiarity with vector databases and RAG patterns for long-context data retrieval.
• Experience shipping systems combining 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, managing prompt design, tool wiring, context routing, failure handling, and output validation.
• Integrate data components across media platforms, ingesting and normalizing data to schema, routing to correct agent context, and monitoring schema drift.
• Develop features with defined success criteria and regression tests, including prompt benchmarking and quality tracking.
• Build and maintain ETL/ELT pipelines supporting automated callouts and optimization reporting, ensuring data freshness and pipeline reliability.
• Extend and operate the MCP connector library for external platform APIs, managing rate limits, retries, and failure modes.
• Build and maintain Slack-based approval workflows for agent callouts, feedback, alerts, and operational notifications.
• Monitor and own the reliability of agents in production, respond to incidents, and implement root-cause fixes.