AI Engineer

This is a fully remote position, open to applicants in Germany.

📋 Description

• Develop, enhance, and sustain AI agents within the frameworks and limitations set by the Lead AI Engineer.

• Take full ownership of your agents from start to finish: including prompt design, tool integration, context management, failure resolution, and output verification.

• Integrate data components across various media platforms — including data ingestion, normalization to schema, and directing to the appropriate agent context.

• Work within established data contracts and identify schema drift before it leads to runtime failures.

• Ensure that no feature progresses to development without clearly defined success criteria and regression tests.

• Conduct prompt benchmarking, monitor output quality across model versions, and proactively identify patterns of hallucination or quality regressions.

• Construct and manage ETL/ELT pipelines that support daily automated callouts and weekly optimization reports.

• Work within and expand the MCP connector library for external platform APIs.

• Create and maintain Slack-based approval processes — including agent callouts, feedback collection, exception alerts, and operational notifications.

• Be responsible for the reliability of your agents in a production environment.

• Monitor output quality, address incidents, and focus on driving root cause solutions instead of temporary fixes.

⛳️ Requirements

• A minimum of 4 years of experience in software, data engineering, ML, or AI platform roles with direct responsibility for production systems.

• Familiarity with media platform APIs such as Google Ads, Meta, DV360, Semrush, and SerpAPI.

• Proficiency in Python and SQL — capable of producing production-grade code, not just analytical scripts.

• Experience with MCP or similar integration layers.

• Hands-on experience in building or managing LLM applications, agent systems, or workflows involving tool-calling.

• Knowledge of workflow orchestration tools like Airflow, Dagster, Prefect, or dbt.

• Expertise in ETL/ELT pipeline design and ensuring data reliability in production — including schema management, contract enforcement, and freshness monitoring.

• Experience with cloud infrastructure such as AWS, GCP, or Azure, and containerized deployments using Docker.

• Ability to define evaluation frameworks and success criteria for model outputs.

• Proficiency in Slack API and workflow automation using webhooks.

• Familiarity with vector databases and RAG patterns for long-context data retrieval.

• Experience in deploying systems that integrate model logic, deterministic business rules, and human approval processes.

• Knowledge of LLM evaluation tools, including token cost tracking, hallucination detection, and model benchmarking.

🏝️ Benefits

• EU BASED ONLY!