Tech Lead, Machine Learning (Real-time AI)

The role

Own the technical vision and architecture for machine learning workflows behind Depo Copilot, Depo Summaries, and the Meetings and Notetaking app. Lead the build of LLM pipelines that reason over case files and live transcripts, and mentor machine learning engineers.

What you will do

• Own the technical vision and system architecture for machine learning workflows.
• Architect and build LLM pipelines that reason over case files and real-time transcripts, with outputs grounded in source material.
• Decide when custom fine-tuning or trained models are needed over prompt engineering, and lead implementation.
• Establish evaluation frameworks with legal experts and annotators, including datasets, rubrics, offline metrics, and release checks.
• Optimize pipeline efficiency, latency, and operational cost for live streaming analysis.
• Transition prototypes into production-grade systems with tests, tracing, and observability.
• Serve as technical lead for incident response during live proceedings.
• Author design documents and partner with Product and other engineering teams on technical plans.
• Mentor machine learning engineers through code reviews, pair programming, and design feedback.
• Communicate technical outcomes and tradeoffs to business stakeholders.

Required qualifications

• Minimum of 5 years building production ML or software systems, including at least 3 years in machine learning roles with end-to-end project ownership.
• Proven technical leadership, including design reviews, setting architectural direction, and mentoring engineers.
• Strong background in NLP and production LLM systems, including retrieval and grounding, long-context reasoning, structured outputs, evaluation, and failure mitigation.
• Experience designing evaluation frameworks for generative AI systems, with datasets and rubrics built alongside domain experts.
• Solid software engineering foundations: API design, data modeling, distributed and asynchronous workflows, testing, and fault tolerance.
• Advanced proficiency in Python and hands-on experience with PyTorch or another deep learning framework.
• Strong written and verbal communication skills in English.
• Ability to meet periodically at the Prague or Bratislava office.
• Legal right to work in Czechia or Slovakia, or willingness to relocate there.

Nice to have

• Experience with real-time or streaming systems.
• Experience with legal domain NLP.

Before you apply

• Open only to candidates residing in, or willing to relocate to, Czechia or Slovakia with the legal right to work in these countries.
• Applications from candidates based outside Czechia or Slovakia are not considered.
• Independent contractor role; contractors handle their own taxes and compliance.

About the company

Filevine is a Legal AI company delivering Legal Operating Intelligence through its LOIS system, which connects context across every legal matter. The company has received AI awards and recognition from Deloitte and Inc. as one of the fastest-growing technology companies in the country.