Department: Engineering
Location: Madrid
Compensation: €95,000 - €115,000 / year
Description
Location: Madrid, Spain
Annual Remuneration: €95,000 - €115,000 and discretionary annual bonus
Pay Frequency: Monthly
Probationary Period: 180 days
Work Arrangement: Hybrid, 3-days per week
TL;DR Kharon is seeking a full-time Madrid-based Senior AI Engineer, Agentic Systems.
Responsibilities
Build and deploy AI agents that can interpret, prioritize, and act on information related to geopolitical and financial signals. This includes:
Develop and continuously improve the tools that connect agents to critical information sources, including web access, semantic and hybrid retrieval, structured-data querying, internal APIs, and knowledge graphs.
Design, implement, and evaluate agentic workflows and multi-agent systems that effectively balance exploration and exploitation, accuracy and latency, and autonomy and control.
Define evaluation frameworks and metrics for retrieval quality, agent performance, factual accuracy, and business relevance.
Partner closely with Research,
Product, and Engineering to rapidly prototype, test, and refine new capabilities through short feedback loops.
Take solutions from prototype to production, including API development, CI/CD pipelines using GitHub Actions, and Kubernetes deployments across multiple environments using core AWS services such as RDS, EKS, and S3.
Own the full lifecycle of the systems and services you build—from architecture and implementation through deployment, adoption, monitoring, maintenance, and continuous improvement.
Qualifications
Interest in or experience with general security, financial crime, sanctions, export controls, or related domains.
5+ years of professional experience in AI engineering, data science, software engineering, data engineering, or a closely related role.
Strong proficiency in Python and SQL.
Proven experience building and operating RAG pipelines and agentic systems in production.
Hands-on ex
📌 Senior AI Engineer, Agentic Systems (Madrid)
🏢 Kharon
📍 Madrid