AI Engineer, Agentic Systems & Quality

FDE Times; San Francisco (CA); Hybrid; USD 200,000 - 280,000; Full time

Benefits offered by this job

Home office stipend

Annual education stipend

Wellness stipend

Healthy lunches

Job summary

Glean, the Work AI platform, is hiring for a senior ML engineer to advance enterprise AI assistants and autonomous agents. You will focus on quality improvements across models and agent harnesses, including hill-climbing, evalsets, and model routing, while collaborating with product and customers.

You will work in a hybrid role in Mountain View or San Francisco, contributing to production systems that power intelligent search, AI assistants, and scalable agents across major workflows.

Qualifications

• 5+ years of industry experience in AI or Machine Learning Engineering.
• Hands-on experience post-training LLMs including adapting open-weight models to specialized tasks.
• Experience building evals for AI assistant and agent systems, including evalsets and LLM-as-a-judge verifiers.
• Strong coding skills in Python and/or Go (TypeScript a plus) and a track record of shipping production ML systems.
• Product-minded, able to turn a vague problem into a concrete experiment, and thrive in a cross-functional team.

Responsibilities

• Use eval results and production traces to improve the stack, including the agent harness, model routing, prompts, and retrieval.
• Work on post-training models with SFT and preference- or reward-based optimization (DPO, PPO, GRPO).
• Build RL environments for simulating enterprise workflows with evalsets and LLM verifiers.
• Improve the quality of evalsets, LLM judges and verifiers, and calibrate them against human graders for release decisions.
• Collaborate with product, platform, and research teams to land quality improvements in production.

Skills

ML Engineering

Post-training LLMs

Eval sets

Python/Go

Product mindset

Tools

Python

Go

TypeScript

Job description

Glean, the Work AI platform, is hiring for a senior ML engineer to advance enterprise AI assistants and autonomous agents. You will focus on quality improvements across models and agent harnesses, including hill-climbing, evalsets, and model routing, while collaborating with product and customers.

You will work in a hybrid role in Mountain View or San Francisco, contributing to production systems that power intelligent search, AI assistants, and scalable agents across major workflows.