Senior Data Scientist - LLM Evaluation (Medhub)

EvolutionIQ(29 days ago)

HybridFull TimeSenior$200,000 - $240,000Data Science

About this role

Senior Data Scientist on the Medhub team responsible for architecting the company’s LLM evaluation framework and ensuring AI products meet rigorous scientific standards. The role emphasizes establishing objective, statistically sound evaluation processes to guarantee model safety, accuracy, and reliability prior to deployment. It partners with domain experts and data teams to translate qualitative expertise into validated evaluation datasets and scalable labeling strategies.

View Original Listing

Required Skills

LLM Evaluation
Experimental Design
Statistical Analysis
Hypothesis Testing
Regression Analysis
Benchmarking
Prompt Auditing
Scorecard Design
Labeling Optimization
Inter-Rater Reliability

+6 more

Qualifications

Master's or PhD in Statistics, Mathematics, or Related Quantitative Field

About EvolutionIQ

evolutioniq.com

EvolutionIQ is an AI-driven claims guidance platform for property & casualty insurers that uses machine learning and advanced analytics to identify, prioritize, and guide high-value claims so adjusters can make faster, more accurate decisions. The platform surfaces actionable recommendations—triage, subrogation and recovery opportunities, fraud flags, and optimal settlement strategies—helping carriers accelerate recoveries and reduce leakage. Integrated into existing workflows, EvolutionIQ focuses on measurable outcomes like faster recoveries, lower costs, and improved operational efficiency, and is chosen for its carrier-focused models and explainable, scalable insights.