AI/ML Infra Engineer: Scale LLM Serving & Pipelines

Glean; Mountain View (CA); Hybrid; USD 175,000 - 270,000; Full time

Benefits offered by this job

Home office stipend

Education stipend

Wellness stipend

Lunches provided

Job summary

Glean, the Work AI platform, is hiring software engineers to build the world’s best search and AI assistant for work. You’ll work on AI/ML infrastructure, generative AI, RAG, and domain-adapted language models, shaping how enterprises access knowledge.

You will design, build, and ship production-ready software, collaborate with modeling and Agentic teams, and maintain scalable infrastructure across cloud deployments. A customer-focused, proactive engineer will thrive here.

Qualifications

• 2–6 years of software development experience.
• BA/BS in computer science, math, sciences, or related degree.
• Production-ready software experience, preferably in AI/ML infrastructure.
• Strong coding skills in Python, Go and Java.
• Customer-focused, team player with ownership mindset.
• Proactive, positive attitude to lead, learn and troubleshoot.

Responsibilities

• Design, build, and improve AI/ML systems and data pipelines infrastructure, including platforms that power large language model serving, routing, and orchestration at scale
• Work with and enable other engineers focused on modeling and Agentic capabilities
• Build agentic systems that monitor, diagnose, debug and maintain infrastructure health across cloud deployments
• Write robust code that's easy to read, maintain, and test
• Mentor more junior engineers, or learn from battle-tested ones

Skills

Python

Go

Java

Education

BA/BS in CS, math, sciences, or related field

Job description

Glean, the Work AI platform, is hiring software engineers to build the world’s best search and AI assistant for work. You’ll work on AI/ML infrastructure, generative AI, RAG, and domain-adapted language models, shaping how enterprises access knowledge.

You will design, build, and ship production-ready software, collaborate with modeling and Agentic teams, and maintain scalable infrastructure across cloud deployments. A customer-focused, proactive engineer will thrive here.