You will get interesting tasks!
RAG Pipeline Optimization
Assess, monitor and continuously improve the performance of our Retrieval-Augmented Generation (RAG) pipeline, Â ensuring high-quality answers to legal queries
Prototype, evaluate, and refine our RAG pipeline to enhance answer accuracy, speed, and cost-efficiency.
Fine-tune large language models (LLMs) to ensure precision and relevance in addressing legal questions.
Data Pipelines & Processing
Design, implement, and maintain robust ETL pipelines for seamless data transformation.
Optimize workflows for storing and managing parsed content in a vector database, enabling efficient retrievalÂ
AI/ML Integration
Develop and improve embedding and chat models to elevate user experience.
Collaborate closely with the software engineering team to seamlessly integrate AI/ML components into the broader product architecture
Production Deployment & Operations
Deploy LLMs and related models in production using Azure cloud infrastructure, ensuring optimal performance and reliability.
Partner with the operations team to automate model deployment through Terraform and other CI/CD tools, ensuring scalability and efficiency