Senior AI Agent Engineer for Production Media

Delvedeeper; Warszawa; Hybrid; PLN 250,000 - 400,000; Full time

Benefits offered by this job

Hybrid working model

Competitive salary

Medicover private medical care

Multisport card

Annual education budget

Employee referral program

Office lunch Tuesdays

Snacks in office

Job summary

Delve Deeper is seeking an experienced, dedicated engineer to build and maintain a multi-agent AI system that automates performance media trading decisions. This is a specialized role in a complex codebase where data quality determines client outcomes and strict evaluation protocols govern every change.

You will own agents end-to-end, integrate data across platforms, and ensure robust pipelines, MCP connectors, and Slack-based workflows while maintaining production reliability and rapid incident

Qualifications

• 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 Python and SQL — production-grade, not just analytical scripts.
• 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; containerized deployments (Docker).
• 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.

Responsibilities

• Agent Development: Build, iterate, and maintain AI agents within the architecture and boundaries defined by the Lead AI Engineer.
• Data Integration: Integrate data components across media platforms and route to the correct agent context.
• Evaluation-First Development: Establish success criteria and regression tests; monitor model outputs across versions.
• Pipeline & ETL Work: Build and maintain ETL/ELT pipelines for daily callouts and weekly reporting; ensure data freshness.
• MCP Connector Work: Extend the MCP connector library for external APIs with resiliency.
• Human-in-the-Loop Workflows: Build Slack-based approval flows for agent calls and alerts.
• Production Reliability: Monitor, respond to incidents, and drive root-cause fixes for agents in production.

Skills

Python

SQL

Airflow

Dagster

Prefect

LLM applications

Slack API

Vector databases

Tools

Google Ads API

Meta API

DV360 API

Semrush API

SerpAPI

Docker

Job description

Delve Deeper is seeking an experienced, dedicated engineer to build and maintain a multi-agent AI system that automates performance media trading decisions. This is a specialized role in a complex codebase where data quality determines client outcomes and strict evaluation protocols govern every change.

You will own agents end-to-end, integrate data across platforms, and ensure robust pipelines, MCP connectors, and Slack-based workflows while maintaining production reliability and rapid incident