Glean
Machine Learning Engineer, Assistant Quality
About this role
Glean is hiring a Machine Learning Engineer to enhance their AI Assistant and autonomous agents by building evaluation frameworks, improving system quality, and shipping production ML systems that power enterprise workflows. You'll work on agent reasoning, retrieval, personalization, and orchestration to make the assistant more reliable and useful.
What you'll do
- Build and improve ML and LLM-powered systems that enhance AI Assistant and agent quality across real user workflows
- Design evaluation, benchmarking, and monitoring frameworks to measure assistant quality and end-to-end system performance
- Develop signals, prompts, and model-driven logic to improve reasoning, planning, personalization, and task completion
- Work on RAG, semantic search, recommendation systems, and agent orchestration to materially improve product outcomes
- Collaborate with product and data teams to translate business needs into measurable quality improvements
- Ship production systems with a focus on practical results over pure research
What they're looking for
- Machine learning systems design and evaluation
- Large language models (LLMs) and prompt engineering
- Retrieval-augmented generation (RAG) and semantic search
- Agent orchestration and reasoning systems
- Python and production ML development
- Data analysis and benchmarking methodologies
- Reinforcement learning or post-training techniques
- Feedback loop and signal design
Opens the application — the Jobs AI extension fills it for you. Set up autofill
Opens the official application on the employer’s site. No login required.
Glean
Glean builds a Work AI platform that helps enterprises access and leverage their internal data intelligently. The company is hiring backend engineers, infrastructure specialists, fullstack engineers, and billing platform leads to develop scalable features, robust data infrastructure, consumption-based billing systems, and enterprise-grade storage and analytics capabilities.
- Website
- glean.com
Likely interview questions
- Walk us through how you've approached measuring quality in a complex ML system—what signals did you prioritize and why?
- Describe your experience building or improving RAG systems. What were the main quality bottlenecks and how did you address them?