AI Engineer – Automation & Data Platform

About the role

We are looking for an AI Engineer to join Crypto Finance Group in Zurich. The role works closely with internal stakeholders across compliance, trading, operations, legal, sales and finance to design and deliver AI‑driven automation solutions. The position starts as soon as possible at our Prime Tower office.

Key responsibilities

• Collaborate with stakeholders across Compliance, Trading, Operations, Legal, Sales, and Finance to identify, scope, and prioritize AI use cases.
• Engineer production data solutions, including deterministic automations, AI agents, RAG systems over internal documents, and structured extraction pipelines.
• Build and maintain the firm’s innovation lab environment for prototyping and evaluating new use cases.
• Maintain reusable, version‑controlled prompt and skill libraries.
• Manage AI governance inventory, documentation, risk classification, model cards, and evaluation artifacts.
• Conduct technical reviews of new AI initiatives and advise on scope, risk, and design choices.
• Contribute to ELT pipelines on the Dagster + SQLMesh + dlt stack for AI data needs.
• Develop the data substrate for AI workloads, including feature views, document indexes, and structured event tables.
• Maintain infrastructure as code in Git with proper review and deployment standards.

Required profile

• 3–6 years of relevant experience as an AI engineer, analytics engineer with AI focus, or data engineer pivoted to AI.
• Demonstrable production experience with large language model (LLM) applications, including structured extraction and agentic patterns, with clear learning from past failures.
• Strong Python programming skills and ability to deliver production‑ready code.
• Working knowledge of LLM evaluation practices (eval sets, regression tests, observability) and understanding of retrieval‑augmented generation and hallucination mitigation.
• Familiarity with at least one orchestrator (Dagster, Airflow, or Prefect) and one transformation framework (SQLMesh or dbt).

Required skills

• Python
• Large Language Model (LLM) applications
• Retrieval‑augmented generation (RAG)
• LLM evaluation (eval sets, regression testing, observability)
• Dagster (or Airflow/Prefect)
• SQLMesh (or dbt)
• ELT pipeline development
• Git (infrastructure as code)
• Data engineering (feature views, document indexes, event tables)