Staff Machine Learning Engineer, Agentic AI Harness & Quality - Moveworks

We need to output HTML fragment with sections for headings where content exists. Must not repeat job title. Must not include boilerplate like EEO, accommodations, export control, etc. Must include only sections with real specific content. We need to parse the job description: It includes Company Description (two paragraphs about Moveworks and ServiceNow). Then Job Description: The Role, What You Get To Do In This Role, Qualifications, Additional Information (Work Personas, etc). We need to remove boilerplate: Work Personas maybe not needed? It's part of Additional Information but might be considered generic? The instruction: Remove cookie/navigation/legal/EEO/equal-opportunity/scam-warning boilerplate, duplicated lines, and application instructions. Work Personas is not exactly legal boilerplate but it's about work flexibility; might be considered part of Additional Information. However we need to include a section only when posting has real, specific content for it. Work Personas is generic description; maybe we can include it under a section like "Additional Information" but we need to see if there is any specific content like "flexible, remote, or required in office". That's somewhat generic but still specific to the role? Might be considered boilerplate. Safer to omit Additional Information entirely, as it's mostly generic. We need sections: About the role? The posting has "The Role" heading. Could map to "About the role" or "Role". The instruction: use

for section headings (e.g. About the role, Responsibilities, Requirements, Qualifications, Skills, Benefits, Pay, Schedule). So we should use those exact headings if content matches. We have content under "The Role": description of role. That could go under "About the role". Then "What You Get To Do In This Role" corresponds to Responsibilities. Then "Qualifications" corresponds to Qualifications. There's also maybe "Skills" but not separate. We could combine qualifications and skills? The instruction: prefer few substantive sections over many thin ones. So we could have About the role, Responsibilities, Qualifications. Possibly also "Skills" if we extract from qualifications? But qualifications already include skills. Might be okay to just have those three. We must not include Pay/Benefits/Schedule because not stated. We must preserve all substantive information; do not invent or summarize away detail. So we need to keep the details from those sections. We need to format lists with

• for any list of duties/requirements/benefits. The responsibilities section includes bullet-like sentences starting with verbs. We can turn each sentence into a
• . Similarly qualifications includes bullet-like items. We need to preserve prose with

  . We must not include duplicated lines. Ensure we don't repeat. Let's extract content. Company Description: Two paragraphs about Moveworks and ServiceNow. This is likely part of "About the role"? Actually company description is separate but could be included under About the role? The instruction: use headings for sections like About the role, Responsibilities, etc. Company description could be part of About the role? Might be better to include a short paragraph under About the role describing the company and role. However the instruction says "Do NOT repeat the job title as a heading (the page already shows it)". It didn't forbid including company description. We can include it as part of About the role

  . Thus About the role section: combine company description paragraphs and the role description from "The Role". But we need to avoid duplication. Let's parse. Company Description: Paragraph1: "Moveworks is 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!" Paragraph2: "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." Then Job Description: The Role paragraph: "We are looking for an experienced software engineer with machine learning expertise to join us in expanding Moveworks agentic AI capabilities, enabling increasingly magical user experiences and improving Moveworks agentic and conversational AI capabilities platform-wide. As a member of the Agentic AI Harness & Quality team, you will have all the tools of modern agentic AI engineering at your disposal, from best-in-class LLMs, multimodal foundation models, and hybrid vector databases to all the infrastructure needed to tune, evaluate, and serve both models and agents in production. We are an eval-driven, data-centric team, and you will have the assistance of a world-class annotation team to build error-free, inclusive, and privacy-preserving datasets for tuning and evaluation. You will also go beyond model training to achieve state-of-the-art AI performance in production, in every meaning of the word “performance”: not just accuracy and quality of outputs, but also latency, reliability, and capability of the end-to-end user-facing system as a whole. Successful machine learning engineers on the team are motivated to design and maintain high-performing compound AI systems, with model training as one tool among many in the toolbox rather than the central responsibility of the job. Our team indexes on increasing our ability to move fast, solving challenging product and engineering challenges, and pushing the envelope of agent reliability and value provided to customers. Your work will impact our team’s core objective to build the highest-performing enterprise assistant platform the world has ever seen, in close collaboration with other functions within Moveworks and ServiceNow as a whole." Then "What You Get To Do In This Role": list of bullet-like sentences: - Apply software engineering, machine learning, and compound AI system engineering to create lasting value for all our customers - Drive quality in agent behavior, both in terms of increasing utility for end users and decreasing misbehavior in the customer business environment - Take on exciting and difficult challenges in AI harness engineering, such as agent cognitive architecture, eval benchmark creation, context engineering, generative UI, dynamic agent orchestration, multimodal I/O, multilinguality, conversational memory management, reasoning strategies, abstractive summarization, grounding and verifiability for generated text, deployment safety, and self-learning - Read, discuss, and build on the latest ML/LLM research and open-source repositories and models - Research and develop innovative, scalable and dynamic solutions to hard problems - Use your knowledge of machine learning fundamentals and LLMs to make improvements to the agentic harness and its AI components, evaluate them with small scale experiments and productionize your solutions at scale - Partner closely with web and chat platform engineering teams to turn harness investments into delightful user experiences that wow our customers Then Qualifications: bullet-like: - Drive to ship product improvements with production-quality, fully unit-tested code and rigorously-evaluated updates to models, prompts, or other tunable system components - Ability to solve problems end-to-end with machine learning - Solid grasp of model evaluation fundamentals, especially for agent trajectories, text generation, text classification, and non-uniform sampling regimes - Attention to detail and high standard of data quality for training and especially evaluation datasets - Readiness to hit the ground running in a Mac development environment, programming in Python and/or Golang - Familiarity with deep learning architectures and algorithms and leading large language models - Desire to work at a startup pace in a medium-sized company with a high degree of ownership - Drive to ship product improvements with production-grade code - Strong appetite for continuous incremental wins and completing challenging projects fast - High level of curiosity about engineering outside of immediate discipline and ongoing desire to learn and stay at the cutting edge of NLU & AI Note there is some duplication: "Drive to ship product improvements with production-quality..." and later "Drive to ship product improvements with production-grade code". Might be considered duplicate but we should preserve all substantive information; but we should avoid duplicated lines. The instruction: remove duplicated lines. So we need to deduplicate. The two lines are similar but not identical; one mentions production-quality, fully unit-tested code and rigorously-evaluated updates; the other mentions production-grade code. Could be considered duplicate-ish but we can keep both? Safer to keep both as they are not exact duplicates. However they are very similar; but we can keep both. Now we need to output HTML. Structure:

  About the role

  ... company description paragraphs + The Role paragraph?

  But we might split: About the role includes company description and role overview. Then

  Responsibilities

  with
  • ...
  . Then

  Qualifications

  with
  • ...
  . We must not include headings with empty content. Let's craft About the role paragraph: combine the two company description paragraphs and the The Role paragraph? Might be too long but okay. We need to preserve all substantive information; we can include them as separate

  elements under the section. Thus:

  About the role

  Moveworks is the Agentic AI Assistant platform ... 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.

  We are looking for an experienced software engineer with machine learning expertise to join us in expanding Moveworks agentic AI capabilities, enabling increasingly magical user experiences and improving Moveworks agentic and conversational AI capabilities platform-wide. As a member of the Agentic AI Harness & Quality team, you will have all the tools of modern agentic AI engineering at your disposal, from best-in-class LLMs, multimodal foundation models, and hybrid vector databases