Extracting structured legal data from email threads using NLP and LLMs for legal-focused AI initiatives.
Requirements
- Proficiency in Python and ML libraries (e.g. scikit-learn, spaCy);
- Strong experience with NLP, LLMs, RAG systems, and frameworks like LangChain or LlamaIndex;
- Experience delivering production-ready ML solutions with monitoring and scalability in mind;
- Ability to integrate Python-based ML models into C-Sharp/Java products or willingness to learn the necessary concepts for smooth handoff.
- Understanding of core ML algorithms (classification, regression, clustering, neural networks);
- Familiarity with cloud platforms (AWS, Azure, or GCP).
Responsibilities
- Develop and refine ML/NLP solutions for diverse legal use cases (e.g. entity extraction from emails);
- Work on projects at different maturity stages — from initial prototyping to improving production systems;
- Translate AI/ML solutions into a format compatible with existing systems (e.g. integration with products written in C-Sharp — no C-Sharp coding required, but you’ll need to understand and prepare integrations);
- Adapt to varying tech stacks — current tools include OpenAI APIs, PostgreSQL, OpenSearch, etc.
Other
- 3+ years of experience in AI/ML Engineering or related fields;
- Collaborate with a cross-functional team, including legal, ML, and infrastructure experts;
- Mentorship : Direct mentorship provided at the start;
- Working Hours : Full CET overlap requiredl
- Locations : Serbia, Poland, Croatia, Portugal.
