Senior AI Engineer - End-to-End LLM & RAG (Remote)

N-iX; España; Híbrido; EUR 90.000 - 120.000; Jornada completa

Ventajas ofrecidas por este puesto de trabajo

Flexible working format

Remote work options

Professional development tools

Descripción de la vacante

N-iX is seeking a Senior Applied AI Engineer for a fast-growing European fintech client. You will design, build and ship customer-facing AI features end-to-end, including RAG systems and agentic workflows, with focus on safe production deployment and rigorous observability.

You will work hands-on on evaluation pipelines, data-fluent retrieval architectures, and guardrails for reliable AI delivery, embedding directly into client squads as an Individual Contributor.

Formación

• Proven experience shipping external customer-facing LLM features to production.
• Hands-on evaluation-pipeline and observability work: drift detection, quality monitoring.
• Data fluency to reason about retrieval architecture independently.
• Agent & harness engineering fluency — guardrails, context and verification layers for safe AI delivery.
• Comfortable with Claude Code and GitHub Copilot as daily tools.

Responsabilidades

• Design, build and ship customer-facing AI features end-to-end.
• RAG system design: chunking, embedding selection, retrieval, re-ranking.
• Ship production LLM-based features with safe deployment practices.
• Work on evaluation pipelines and observability: drift detection, quality monitoring.
• Reason about retrieval architecture with strong data fluency.
• Develop guardrails, context and verification layers for reliable AI delivery.
• Embed into client squads as an individual contributor.

Conocimientos

Python

RAG design

LLM deployment

Evaluation pipeline

Observability

Data fluency

Guardrails

Herramientas

Claude Code

GitHub Copilot

AWS Bedrock

OpenAI APIs

Langfuse

Descripción del empleo

N-iX is seeking a Senior Applied AI Engineer for a fast-growing European fintech client. You will design, build and ship customer-facing AI features end-to-end, including RAG systems and agentic workflows, with focus on safe production deployment and rigorous observability.

You will work hands-on on evaluation pipelines, data-fluent retrieval architectures, and guardrails for reliable AI delivery, embedding directly into client squads as an Individual Contributor.