AI Engineer - Agentic Systems & Evaluation

Glean; San Francisco (CA); Híbrido; USD 200.000 - 280.000; Jornada completa

Ventajas ofrecidas por este puesto de trabajo

Home office stipend

Education & wellness stipends

Daily healthy lunches

Descripción de la vacante

Glean is seeking an AI/ML engineer to advance the quality of enterprise AI assistants and autonomous agents. You will work at the intersection of applied research, quality, and product engineering to improve models and agent systems.

You will help build eval environments, calibrate judges, and push improvements across the stack, collaborating with product teams and customers to deliver reliable, scalable AI capabilities.

Formación

• 5+ years of AI/ML engineering experience.
• Hands-on post-training LLMs experience.
• Experience building evals for AI assistants and agent systems.
• Strong coding in Python and/or Go; TS a plus; production ML experience.
• Product-minded, able to turn vague problems into experiments.

Responsabilidades

• Improve the entire stack using eval results and production traces.
• Develop post-training models with SFT and reward-based optimization.
• Build RL environments for enterprise workflows and evaluators.
• Improve evalsets, LLM judges, and verifiers for scoring quality.
• Collaborate with product, platform and research teams to land quality improvements.

Herramientas

Python

Go

TypeScript

Descripción del empleo

Glean is seeking an AI/ML engineer to advance the quality of enterprise AI assistants and autonomous agents. You will work at the intersection of applied research, quality, and product engineering to improve models and agent systems.

You will help build eval environments, calibrate judges, and push improvements across the stack, collaborating with product teams and customers to deliver reliable, scalable AI capabilities.