(USA) Principal, Data Scientist - Gen AI Vision
职位介绍
Own the evaluation architecture for AI agents, designing how success is measured across non-deterministic outputs.
Lead the brain that critiques agents with a mix of LLM-based judging, human benchmarks, and automated pipelines.
Develop evaluation pipelines, calibrate prompts, and distill smaller judge models balancing accuracy, latency, and cost.
Curate large-scale conversation data to build reliable Golden Set datasets and standardized ground truth for subjective tasks.
Collaborate with engineering to integrate quality signals into CI/CD pipelines for automated testing and monitoring.
Drive insights to identify systemic weaknesses, mentor data scientists, and advance best practices in AI evaluation.
Lead the brain that critiques agents with a mix of LLM-based judging, human benchmarks, and automated pipelines.
Develop evaluation pipelines, calibrate prompts, and distill smaller judge models balancing accuracy, latency, and cost.
Curate large-scale conversation data to build reliable Golden Set datasets and standardized ground truth for subjective tasks.
Collaborate with engineering to integrate quality signals into CI/CD pipelines for automated testing and monitoring.
Drive insights to identify systemic weaknesses, mentor data scientists, and advance best practices in AI evaluation.
查看完整职位
工作职责、任职要求、技能与福利 — 免费创建账号即可查看。
或
已有账户？
登录相似职位
其他可能适合您的职位。