Data & Analytics Engineer - AI Platform team (Hybrid)

Role Description

As a Data & Analytics Engineer, you will own the data lifecycle that powers our AI customer care platform—spanning voice, chat, and email channels. Your mission is to build the robust infrastructure, data models, and observability tools that ensure our AI agents are reliable, context-aware, and performant.

You are an engineer who values high-velocity development and clean data architecture. You will design the pipelines that feed our RAG/CAG (Retrieval/Context Augmented Generation) systems and build the "analytical conscience" of the platform—turning raw interaction logs into structured KPIs and visual dashboards that prove our AI's value.

Main Responsibilities

Data Engineering & Pipelines

• Design and operate reliable data pipelines using Python and SQL to ingest and transform interaction data from voice and text channels.
• Manage the data lifecycle within our core databases: PostgreSQL for structured application data and Elasticsearch for search and retrieval.
• Build and maintain scalable dbt projects to transform raw logs into high-quality, governed data models.

Analytics, KPIs & Visualization

• Act as a Data Analyst expert: collaborate with stakeholders to define key performance indicators (KPIs) like resolution rates, intent accuracy, and cost-per-interaction.
• Build and maintain business-facing dashboards in Looker and internal data applications in Streamlit.
• Translate complex technical traces into actionable insights for the product and business teams.

RAG/CAG Infrastructure

• Own the "Retrieval" layer: optimize how data is indexed and queried in Elasticsearch to improve AI response context.
• Develop the pipelines that manage chunking, metadata tagging, and context window optimization.

Data & Pipeline Observability

• Instrument our data pipelines and AI services with Prometheus and Grafana to monitor data quality, processing latency, and pipeline throughput.

Design proactive alerting frameworks for data stalls, schema changes, or AI context-retrieval delays

We Are Looking For

Core Technical Stack

• Python & SQL Skills: Deep experience writing clean, maintainable code for data processing.
• AI-Assisted Development: High proficiency in using AI tools (e.g., Claude Code, Cursor, or other LLMs) to accelerate your coding, debugging, and documentation process.
• Modern Data Stack: Expert-level experience with dbt and cloud data warehousing/databases.
• Database Management: Hands-on experience operating and optimizing PostgreSQL and Elasticsearch.
• BI & Apps: Experience designing and building interactive tools with Streamlit.
• Observability: Experience using Prometheus and Grafana for application-level, pipeline, and data-quality monitoring (rather than pure infrastructure management).

Nice to Have (The "Bonus" Skills)

• LLM Evaluation (High Priority): Experience building automated evaluation frameworks; understanding of metrics like Faithfulness, Relevancy, and Hallucination rates.
• RAG/CAG Domain Knowledge: Familiarity with the mechanics of Retrieval Augmented Generation and how to optimize vector/keyword search.
• Speech & Audio: Experience with transcription pipelines, audio normalization, or telephony data.
• Customer Care Background: Experience working with contact center data, conversational analytics, or CRM integrations.
• Experience designing reports in Looker

Benefit

• Hybrid working model.
• Flexible working hours through trust-based working hours.
• At some locations a subsidized canteen and various free drinks.
• Modern office space with very good transport connections.
• Various employee discounts for activities and products.
• Employee events such as summer and winter parties, as well as workshops.
• Numerous training and development opportunities.
• Various health offers, such as sports and health courses.