AI Engineer - Multi-Agent Production ML (EU)

Delve; Polska; Hybrid; PLN 240,000 - 360,000; Full time

Job summary

Delve Deeper, a performance media agency, seeks a dedicated individual contributor to build and maintain a multi-agent AI system that automates media trading decisions. You will work on a complex codebase, design prompts, wire tools, and ensure data quality with strict evaluation protocols.

You will own data integration across platforms, enforce schemas, run regression tests, and develop ETL/ELT pipelines for daily operations and weekly reporting.

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).
• 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.

Responsibilities

• Build, iterate, and maintain AI agents within architecture defined by Lead AI Engineer.
• Integrate data across media platforms and route to correct agent context.
• Ensure defined success criteria and regression tests for features before development.
• Develop and maintain ETL/ELT pipelines for daily calls and weekly optimisation reporting.
• Extend MCP connector library for external platform APIs; manage rate limits and failures.
• Create Slack-based approval flows and operational notifications for human decisions.
• Monitor production reliability; drive root-cause fixes and communicate risks to leadership.

Skills

Python

SQL

LLM applications

Agentic systems

Tool-calling workflows

Data engineering

Cloud infrastructure

Evaluation frameworks

Production ownership

Slack API

Vector databases

Tools

Airflow

Dagster

Prefect

dbt

AWS

GCP

Azure

Docker

Job description

Delve Deeper, a performance media agency, seeks a dedicated individual contributor to build and maintain a multi-agent AI system that automates media trading decisions. You will work on a complex codebase, design prompts, wire tools, and ensure data quality with strict evaluation protocols.

You will own data integration across platforms, enforce schemas, run regression tests, and develop ETL/ELT pipelines for daily operations and weekly reporting.