21 hours ago
Berlin, GermanySenior
Responsibilities
- Build and operate document intelligence systems for extraction, classification, and processing of accounting and tax documents.
- Design and implement retrieval and knowledge systems across tax law, internal knowledge, client histories, and firm-specific data.
- Build agentic workflows and AI-driven automation for multi-step accounting and tax processes.
- Develop prediction, suggestion, anomaly detection, classification, and recommendation systems.
- Build and maintain data pipelines and infrastructure for reliable AI and ML workflows.
- Design evaluations, monitoring, observability, and feedback loops for production AI systems.
- Improve AI capabilities using real-world performance data and collaborate with engineers, operations staff, and tax professionals.
Requirements
- At least 3 years of hands-on experience shipping ML, LLM, or AI-based systems into production.
- Production experience with LLMs, retrieval systems such as RAG, or AI agents.
- Experience building document intelligence systems for unstructured document extraction, classification, and understanding.
- Strong software engineering discipline focused on testing, reliability, observability, and maintainability in AI systems.
- Experience designing evaluation frameworks and monitoring systems for AI in production.
- Ability to take AI capabilities from prototype through iterative production deployment.
- Experience translating complex workflows into AI solutions with domain experts.
- Background in high-stakes domains where reliability and auditability are critical.
- Exposure to accounting, tax, or financial workflows is preferred.
- Production experience with agentic workflows, anomaly detection, classification, or recommendation systems is preferred.
Benefits
- On-site work in Berlin, Germany.