LLM Ops Engineer - Litera - Denver, CO

Job Description

Join the Legal Tech Revolution at Litera
Are you ready to shape the future of how law is practiced? At Litera, we’re on a mission to Raise The Bar™️ for the legal profession by delivering transformational and globally-trusted solutions to law firms and corporate legal teams worldwide. We’ve been a leader in legal tech innovation for 30 years and are leading the legal AI revolution to this day with most of the world’s largest law firms as our clients. If you’re passionate about building AI-forward solutions that scale globally and want your work to impact millions of legal professionals worldwide, this is your opportunity to be part of an extraordinary team that’s elevating the craft of law.

This position is based in Denver, Colorado or Raleigh, NC and candidates should reside within reasonable commuting distance, as this role requires on-site presence at least three days per week.

About the Role
We are seeking an experienced LLM Engineer to join our newly established LLM Ops Team. In this role, you will be responsible for managing the complex lifecycle of Large Language Models from development to deployment, monitoring, and continuous improvement.

Key Responsibilities:
Model Development & Training
• Fine-tune pre-trained models for specific use cases
• Curate and prepare datasets for training
• Manage training infrastructure, resources, and computational environments
• Implement optimization techniques to improve model performance

Deployment & Serving
• Develop and manage APIs for model serving
• Scale infrastructure to handle varying demand loads
• Build and maintain the GenAI middleware/sidecar layer
• Integrate LLMs with existing systems and data sources

Monitoring & Evaluation
• Track performance metrics including latency and throughput
• Monitor quality metrics such as hallucination rates and accuracy
• Optimize costs associated with model inference and training
• Create and maintain dashboards for real-time performance insights

Testing &