About this role
Applied Data Scientist, LLM Evaluation at Driver. Location: Austin or Austin. Role: Define metrics, Build pipelines, Evaluate results Requirements: 3-5 years in applied science/ML with evaluation focus; strong statistics; Python; NLP/LLM evaluation; data pipelines and AB testing; ability to design rubrics. Category: Data and Analytics Seniority: Mid Level Tools: Python, pandas, NumPy, scipy, sklearn, Jupyter, LLM APIs, Airflow, Dagster, SQL, Matplotlib, Plotly, Streamlit, RBAC, annotation pipelines Commitment: Full Time Workplace: Remote Languages: English