AI Evaluation Leader & Platform Architect

Glean; Mountain View (CA); Hybrid; USD 250.000 - 350.000; Vollzeit

Benefits dieser Stelle

Home office stipend

Education stipend

Wellness stipend

Free lunches

Zusammenfassung

Glean is hiring for an AI Evaluation Engineer to lead end-to-end evaluation strategy for GenAI products. You will design scalable evaluation infrastructure, curate representative data sets, and implement robust metrics to guide releases and product decisions.

You will build deterministic and human-evaluated scoring, integrate these into CI and pre-release suites, and mentor a high-performing team across product, engineering, and security.

Qualifikationen

• 10+ years in software engineering, ML infra, data systems or related field.
• 5+ years in engineering or applied AI team management, with leadership track record.
• Hands-on experience designing or operating evaluation systems for LLM/GenAI products.
• Familiarity with evaluation methods, benchmarks and diagnostics.
• Understanding of agent evaluation, tool use, and safety testing is a plus.
• Strong coding in Python or other production languages; solid API and distributed system skills.
• Experience building scalable data or developer platforms; cloud infra, Kubernetes, observability is beneficial.

Aufgaben

• Own the AI evaluation eng roadmap and technical direction end to end.
• Build scalable evaluation infrastructure for datasets, graders, replay, result analysis and dashboards.
• Create and maintain representative evaluation sets from expert examples and real signals; guard held-out sets.
• Define a balanced quality measurement system covering correctness, grounding, retrieval, and task success.
• Develop deterministic checks, model-based graders, and human evaluation with clear rubrics.
• Integrate evaluation into CI, pre-release suites, and production feedback loops.

Kenntnisse

Python

Production systems

Distributed systems

APIs

CI/CD

Kubernetes

Observability

Leadership

Team management

Product thinking

Ausbildung

MS/PhD in Computer Science, AI or related field

Tools

Kubernetes

Cloud platforms

Data stores

CI/CD tooling

Jobbeschreibung

Glean is hiring for an AI Evaluation Engineer to lead end-to-end evaluation strategy for GenAI products. You will design scalable evaluation infrastructure, curate representative data sets, and implement robust metrics to guide releases and product decisions.

You will build deterministic and human-evaluated scoring, integrate these into CI and pre-release suites, and mentor a high-performing team across product, engineering, and security.