6 months ago
Milan, ItalySenior
Responsibilities
- Design and build agent-driven and RAG-based AI systems for complex legal tasks.
- Fine-tune and post-train LLMs using supervised and reinforcement learning techniques.
- Develop and optimize large-scale search pipelines for LLM-powered agents.
- Implement NLP algorithms to extract, structure, and validate information from legal documents.
- Run end-to-end evaluations to identify bottlenecks and measure performance.
- Collaborate with legal experts to design evaluation protocols and build domain-specific datasets.
- Follow coding standards, engineering best practices, and rigorous code-review processes.
Requirements
- Proven expertise building and managing robust ML pipelines.
- Strong Python skills with hands-on experience in LLM research and deep learning systems.
- Knowledge of full-text search, vector databases, or other large-scale retrieval systems.
- Ability to collaborate with legal experts, researchers, and engineers.
- Familiarity with MLOps and integrating ML models into production backends is a strong plus.
- Up-to-date knowledge of LLM innovation, ideally including pre-training or deploying large-scale models in real-world scenarios.
Benefits
- Annual salary range of €45,000–€100,000.
- Equity package, health coverage, meal vouchers, performance bonuses, and team retreats and off-sites.
- Hybrid work arrangement balancing remote work with in-person collaboration at the Milan headquarters.
Tech Stack
Categories
About Lexroom
Lexroom builds an AI-powered legal research and drafting platform for law firms and in-house legal teams, producing source-backed answers and first drafts across multiple practice areas. It sells the software as a subscription with enterprise features to integrate into lawyers’ workflows, developed with input from firms such as GOP, Ichino Brugnatelli, and GPBL. The privately held company is headquartered in Milan and raised a Series B in 2026.