AI Engineer

Stack

Responsibilities

• ▹Build, iterate and maintain AI agents within the architecture defined by the Lead AI Engineer; own your agents end to end (prompt design, tool wiring, context routing, failure handling, output validation)
• ▹Integrate data from media platforms: ingest, normalize to schema, route to the correct agent context, and surface schema drift before it becomes a runtime failure
• ▹Evaluation-first development: success criteria and regression tests for every feature, prompt benchmarking, tracking output quality across model versions, flagging hallucination patterns and regressions
• ▹Build and maintain ETL/ELT pipelines for daily automated callouts and weekly optimisation reporting, owning data freshness and pipeline reliability
• ▹Operate and extend the MCP connector library for external platform APIs, handling rate limits, retries and failure modes
• ▹Build and maintain Slack-based approval flows: agent callouts, feedback capture and exception alerts
• ▹Own agent reliability in production: monitor output quality, respond to incidents, drive root-cause fixes, and alert the Lead AI Engineer early to delivery risks

Requirements

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

Soft skills

About the company

Delve Deeper is a performance media agency focused on the charity and nonprofit sector, working with organizations that invest $5M-$20M annually in media. It helps clients with advanced analytics, intent-based audience segmentation and full-service media management.