18 sep
|
CaseWare
|
Colombia
Caseware is seeking an experienced staff-level applied scientist to design experiments and evaluate GenAI-powered audit agents. You will own evaluation frameworks, benchmarks, and thresholds while building AI tools for the agent builder experience. The role emphasizes rigor, experimentation, and collaboration with security and domain SMEs.
You will lead memory-related research for agentic systems, promote best practices, and mentor others, all within a fully remote position based in Colombia.
📌 Remote GenAI Evaluation Architect (Colombia)
🏢 CaseWare
📍 Colombia