Search
Go
Senior Data Scientist, AI Evaluations Platform
Summary by AIEngineer.careers
Senior Data Scientist, AI Evaluations Platform is a LLM Evaluation Engineer role (full-time). with En Us. in TORONTO, CA. Imported listing (source: rbc.wd3.myworkdayjobs.com). Apply on the employer's site (rbc.wd3.myworkdayjobs.com).
Imported listing (source: rbc.wd3.myworkdayjobs.com) · Apply on rbc.wd3.myworkdayjobs.com
TORONTO · CA
—
Full-time
SENIOR
The sections below reproduce the third-party job description for reference. AIEngineer.careers does not write or control this text.
Imported job description
Sourced from rbc.wd3.myworkdayjobs.com
This Senior Data Scientist role focuses on developing and refining evaluation frameworks for generative AI and agentic systems. Key responsibilities include designing scoring mechanisms, establishing benchmarks, and creating human evaluation protocols to guarantee model safety, quality, and performance at scale. The position requires strong analytical skills and expertise in AI model assessment methodologies.
Responsibilities
- Design and build evaluation frameworks for generative AI and agentic systems
- Develop scoring mechanisms and performance benchmarks
- Create and manage human evaluation protocols
- Ensure model safety, quality, and scalability across deployments
Requirements
- Strong background in data science, statistics, or machine learning
- Experience evaluating generative AI models and agentic workflows
- Expertise in benchmarking, scoring methodologies, and metric design
- Ability to translate qualitative feedback into quantitative evaluation frameworks
Nice to Have
- Experience with LLM evaluation tools and automated testing pipelines
- Background in human-in-the-loop (HITL) evaluation processes
En Us
Toronto · CA · 101000+ employees
RBC is a global financial institution and Canada's largest bank by market capitalization. It offers personal and commercial banking, wealth management, insurance, investor services, and capital markets products to millions of clients worldwide.
