Senior AI Engineer - Production ML & Guardrails (Remote)

Engaige; Utrecht; Híbrido; EUR 90.000 - 130.000; Jornada completa

Ventajas ofrecidas por este puesto de trabajo

Stock options

Growth opportunities toward CTO

Descripción de la vacante

Engaige Technologies B.V. is building an AI customer-service platform for e-commerce. As a Senior AI Engineer, you’ll own evaluation, retrieval, and policy-driven workflows ensuring safe, scalable production models across multiple providers.

You’ll work closely with the Head of Product and CEO to set technical standards and drive improvements across the team. Our stack includes Python, Weaviate, Langfuse, OpenTelemetry, and Google Cloud Platform.

Formación

• Experience shipping ML models to production.
• Strong understanding of offline/online evaluation and A/B testing.
• Proficiency in Python and backend production code.

Responsabilidades

• Own evaluation methodology for agents and benchmarks with real production conversations.
• Design offline evaluations predicting online behavior and align benchmarks with production results.
• Build live guardrails, monitoring, and staged rollout across model providers.
• Improve retrieval and classification including RAG and embedding-based categorization.
• Develop policy graphs enabling step-by-step agent behavior.
• Extend AI manager to identify knowledge gaps and drive weekly improvements.
• Collaborate with the Head of Product and CEO to set engineering standards.

Conocimientos

Python

Backend production code

Machine learning in production

Evaluation & AB testing

RAG / vector search

LLMs in production

Weaviate

Langfuse

Google Cloud Platform

Herramientas

Weaviate

Langfuse

OpenTelemetry

Google Cloud Platform

Descripción del empleo

Engaige Technologies B.V. is building an AI customer-service platform for e-commerce. As a Senior AI Engineer, you’ll own evaluation, retrieval, and policy-driven workflows ensuring safe, scalable production models across multiple providers.

You’ll work closely with the Head of Product and CEO to set technical standards and drive improvements across the team. Our stack includes Python, Weaviate, Langfuse, OpenTelemetry, and Google Cloud Platform.