Software Engineer, Evals

Responsibilities

• Design and build large-scale evaluation pipelines to measure assistant and agent quality
• Evaluate frontier model releases and OSS model drops to understand regressions and tradeoffs
• Build agent observability infrastructure including trace enrichment and telemetry pipelines
• Own backend systems from architecture and design through production rollout and monitoring
• Partner with product, ML, and infrastructure engineers to integrate evals into the shipping process
• Improve the quality loop by connecting eval results and customer feedback to product improvements
• Mentor other engineers and help shape the engineering culture in Bangalore

Requirements

• 4+ years of software engineering experience in backend systems, infrastructure, or distributed systems
• Strong coding skills in Go, Python, Java, or C++
• Experience with distributed data pipelines, production services, or cloud-native infrastructure
• Analytical rigor regarding metrics and user experience
• Ability to work in customer-focused, cross-functional environments

Preferred Qualifications

• Experience with LLM applications and evals
• Experience with tracing, data warehouses, or workflow orchestration
• Experience with ML infrastructure

About the Company

Glean is the Work AI platform that helps everyone work smarter with AI. It provides an enterprise-grade ecosystem for intelligent search, AI assistants, and scalable AI agents, helping organizations govern and customize AI across their entire business.