Staff Machine Learning Engineer, Agent Eval Platform

Company Description

Who we are

Moveworks: the Agentic AI Assistant platform that empowers the entire workforce.

Our platform enables employees to converse with all of their business systems through natural language to quickly find answers and automate tasks. Powered by the world's most advanced LLMs, our proprietary models, and a sophisticated Agentic AI platform, we're transforming how work gets done by allowing AI to take initiative, streamline complex workflows, and continuously learn and adapt.

Moveworks is trusted by over 5.5 million employees at more than 350 of the world’s largest companies, including 10% of the Fortune 500, to automate everyday tasks and streamline business operations. Recognized on the Forbes Cloud 100 and AI 50 lists, Moveworks was also named one of Fast Company’s 2025 Most Innovative Companies and Inc’s Best in Business, in the Best in Innovation category. Moveworks was also recognized at Microsoft’s 2025 Partner of the Year and in 2024, received the AI Breakthrough Award.

In December 2025, Moveworks was acquired by ServiceNow, marking a pivotal milestone in our journey to create a single front door to work for all business systems. By combining ServiceNow’s leading workflow automation with Moveworks’ Reasoning Engine and natural language capabilities, we deliver the AI platform for every person and every workflow. Built to go beyond basic summaries to deliver meaningful business impact. Together, our AI acts across enterprise systems to turn conversations into completed work.

By joining our team, you’ll be at the forefront of the AI transformation, backed by the global scale of ServiceNow and the agility of a high-growth company. We are looking for world-class talent to help us extend agentic AI to every employee across every corner of the business. Come join us!

ServiceNow: it all started in sunny San Diego, California in 2004 when a visionary engineer, Fred Luddy, saw the potential to transform how we work. Fast forward to today — ServiceNow stands as a global market leader, bringing innovative AI-enhanced technology to over 8,100 customers, including 85% of the Fortune 500®. Our intelligent cloud-based platform seamlessly connects people, systems, and processes to empower organizations to find smarter, faster, and better ways to work. But this is just the beginning of our journey. Join us as we pursue our purpose to make the world work better for everyone.

Job Description

The Role

Moveworks' AI agents don't just generate text — they act. They plan, call tools, and change real state in enterprise systems on behalf of 5.5 million employees. Building agents is no longer the bottleneck. Improving them is: knowing whether a change made the agent better, why a conversation failed, and which part of the system should be fixed.

You'll build the loop that makes our agents improve themselves — finding failures in real use, deciding which part of the agent harness is responsible, checking every proposed fix on cases the fixer never saw, and turning each fixed failure into a permanent test. We improve the system around the model: instructions, tool descriptions, routing, knowledge and memory. We don't train the model itself.

The work is blend of ML and systems engineering. You'll decide whether a signal is trustworthy enough to act on, and build the infrastructure that produces that signal reproducibly across hundreds of customer organizations.

This isn't a model-training role, and it isn't a testing role. It's applied ML at a point where the methodology genuinely isn't settled: LLMs judging LLMs is an open research problem, and we're working it against agents that take real, irreversible actions in stateful, multi-tenant enterprise environments.

What you get to do in this role

Judge design and calibration

• A shared base judge with per-item rubrics expressed as configuration next to the dataset — so eval authors express intent, rather than forking a prompt per eval
• Splitting the problem correctly: deterministic validators for checkable world state ("was the ticket created, with the right item, routed to the right approver?"), and an LLM judge for the parts that are genuinely fuzzy — was the clarifying question appropriate, was policy followed, was the path efficient
• Scoring that reports its own confidence , so uncertain judgements route to a human instead of quietly becoming trusted signal
• A standing calibration loop against human-labeled trajectories, run in partnership with our annotation team — they own the human labeling, you own the calibrated judge artifact. How consistently humans agree with each other sets the ceiling on how good any judge can be, so raising that ceiling is part of the job
• Guarding against correlated blind spots: our user simulator and our judge are both LLMs, and they can be wrong in the same direction
• Offline↔online divergence: when simulation and production disagree, being the person who can say why, and keeping the suite re-seeded from new production failures so it can't quietly overfit

Self-improving agent harness

This is where the pillar is headed, and a large part of why the seat exists. You'll build the components that let the agent harness get better from its own use, without changing the model underneath.

• Finding what to improve: surfacing where the agent falls short in real use, including failures that look like success
• Synthetic data and environments: generating scenarios and the seeded enterprise worlds they run in — with expected outcomes and checks — from real failures or ahead of what customers ask for, and making sure what gets generated is realistic, hard enough, and doesn't leak the answer
• Deciding where a fix belongs: understanding why the agent failed and which part of the harness should change: its instructions, tools, routing, knowledge or memory
• Proposing improvements: optimizing those components against simulation rather than against production traffic
• Checking before anything ships: verifying eve