We are looking for an experienced Machine Learning Engineer (f/m/d) to join our growing engineering team. In this role you will take part in all the data-related activities at Certivity - from information extraction and document parsing to model training and inference. You will have a chance to apply cutting edge NLP techniques to real-world problems in the regulatory domain. As a part of our small (but growing) team you will have a unique opportunity to shape the product and the company.

• You will integrate, fine-tune, and deploy large language models (LLMs) for text classification, summarization, and entity extraction.
• You will maintain and improve our semantic search system.
• You will collaborate with other engineers and domain experts to come up with robust and convenient interfaces between different parts of the platform.
• You will evaluate and benchmark LLM performance against traditional ML approaches to ensure quality and efficiency.
• You will learn, maintain, and improve the internal data model.
• Stay current with rapidly evolving LLM research and best practices.
• Grow in your role personally and professionally.

• You have a strong background in machine learning, theory, and practice.
• You have hands-on experience implementing and maintaining production ML systems in Python.
• Experience working with large language models (LLMs), including prompt engineering, fine-tuning, evaluation methodologies, and building LLM-powered agents is a plus.
• Experience with search technologies such as Elasticsearch or Mongo Atlas Search, implementing semantic search, hybrid search approaches, query expansion techniques, and reranking methodologies is a plus.
• You have experience with at least one cloud platform, i.e., Microsoft Azure
• You write clear, well-tested, and maintainable code.
• Fluent spoken and written English (company language is English).

• hybrid work in Munich, in exception 100% remote work is also possible if you live in Germany
• flexible working time
• 30 days of vacation per year
• 30 days of workcation per year, in the EU and some selected countries
• high autonomy and flat hierarchies
• direct access to the users, quick iteration cycles