Founding Engineer

Postaladdress

Berlin, Germany

7 days ago

Apply on startup.jobs

Prepare application

Role details

Contract type

Permanent contract

Employment type

Full-time (> 32 hours)

Experience level

Experienced

Experience required

3 years minimum

Working hours

Regular working hours

Job source

startup.jobs

Tech stack

Artificial Intelligence Automated Storage and Retrieval Systems Monitoring of Systems Knowledge-Based Systems Recommender Systems Software Engineering Large Language Models

Job description

This is a founding engineering role at an early-stage company building AI systems that reduce manual work inside real tax advisory and accounting firms. You will work directly with production workflows and domain experts, taking AI from prototype to reliable, auditable systems that handle high-stakes financial data at scale., * Build and operate document intelligence systems that extract, classify, and process complex accounting and tax documents.

Design and implement retrieval and knowledge systems (RAG) across tax law, internal knowledge bases, client histories, and firm-specific data.
Build agentic workflows and AI-driven automation for multi-step accounting and tax processes.
Develop prediction and suggestion systems for use cases such as booking proposals, anomaly detection, classification, and intelligent recommendations.
Build and maintain data pipelines and infrastructure to power reliable AI and ML workflows.
Design evaluations, monitoring, observability, and feedback loops to understand system performance and failure modes in production.
Continuously improve AI capabilities based on real-world performance data.
Collaborate closely with engineers, operations staff, and tax professionals to translate domain knowledge into AI solutions.

Requirements

3 or more years of hands-on experience shipping ML, LLM, or AI-based systems into real production environments.
Hands-on experience with LLMs, retrieval systems (RAG), or AI agents in production.
Experience building document intelligence systems covering extraction, classification, and understanding of unstructured documents.
Strong software engineering discipline: testing, reliability, observability, and maintainability in AI systems.
Experience designing evaluation frameworks and monitoring systems for AI in production.
Demonstrated ability to take AI capabilities from prototype through iterative production deployment.
Experience collaborating with domain experts to translate complex workflows into AI solutions.
Background in high-stakes domains where reliability and auditability are critical.
Exposure to accounting, tax, or financial domain workflows is a plus.
Experience with agentic workflows, anomaly detection, classification, or recommendation systems in production is a plus.