Job Description
We are on a lookout for a hands-on Principal ML Engineer (Agentic AI) to join the Vendor Data Team on our journey to always deliver amazing experiences to go beyond prompt engineering into autonomous orchestration: designing agents that generate their own prompts, tools that empower AI with real-world actions, and judge models that validate outputs. Your work won’t sit in research notebooks — it’ll ship.
As part of our Vendor Team, you’ll be the driving force behind the success of thousands of restaurants, shops, and local businesses. Your contributions will empower vendors with advanced tools to manage their operations, boosting their visibility and reach. Every feature you help build will create growth opportunities for businesses of all sizes, strengthening Delivery Hero’s ecosystem and impact.
In the Vendor Data Team we build AI-native products that operate businesses. At our core is a 360° AI Account Manager for food delivery platforms—a system that moves beyond static ML pipelines to reason, act, and automate architecture integrates large-scale data pipelines, retrieval systems, and agentic components to drive real-world decisions. We believe a model is only as good as its environment; therefore, we prioritize data quality, system design, and infrastructure reliability. As an agentic-first team, we use tools like Claude Code to ensure AI actively participates in development, always grounded in robust engineering practices.
Key Responsibilities:
1. Design and own end-to-end ML and data systems — from ingestion and transformation to model integration and production deployment
2. Architect and maintain scalable data pipelines for RAG, embeddings, and real-time/near-real-time data processing
3. Build and operate production-grade ML services and APIs, ensuring reliability, scalability, and performance
4. Define standards for infrastructure, deployment, and system reliability, including Infrastructure as Code, containerization, and orchestration
5. Integrate ML systems with external APIs, tools, and operational platforms, enabling real-world actions and automation
6. Lead the implementation of security best practices for AI systems, including secure prompt handling, data privacy protocols, and protection against adversarial attacks or model injection. Ensure all AI agents operate within strict authorization boundaries.
Qualifications
7. Strong experience designing and scaling production-grade ML systems and data platforms, including large-scale deployments
8. Deep expertise in data engineering and ML pipelines, including feature/data pipelines, RAG systems, and embedding workflows
9. Proven experience building and maintaining reliable data infrastructure with strong guarantees around data quality and freshness
10. Strong engineering skills in Python and SQL, with experience in Docker, Kubernetes, and cloud environments
11. Experience with Infrastructure as Code (, Terraform or similar) and building reproducible, scalable systems
12. Hands-on experience integrating ML systems with real-world APIs and services, and operating them in production with monitoring and observability
Nice to have:
13. Experience with LLMs, agent architectures, or orchestration frameworks (LangGraph, AutoGen, CrewAI, etc.)
14. Familiarity with synthetic data generation, evaluation systems, or AI feedback loops
15. Experience with agent or ML observability tools such as Langfuse or LangSmith
16. Experience with model serving, routing, or inference optimization
17. Experience with open-source models (, LLaMA, Mistral, Mixtral) or custom inference stacks
18. Knowledge of system reliability, failure handling, and safety patterns in AI systems