Staff AI Engineer, Agentic AI Harness & Quality - Moveworks

The Role We are looking for an experienced software engineer with expertise building AI-native product and platform to join us in expanding ServiceNow’s customer-facing agentic AI capabilities. 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 frontier LLMs and tools to all the infrastructure needed to tune, evaluate, and serve AI 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 evals. You will push the envelope of 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 AI engineers on the team are motivated to design and maintain high-performing compound AI systems. 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. What you get to do in this role: • Apply software engineering and compound AI system engineering to create lasting value for all our customers • Drive quality in agent behavior, both in terms of increasing success rate at achieving goals set by 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 such as image and voice, multilinguality, conversational memory management, reasoning strategies, grounding and verifiability for generated text, deployment safety, and automatic harness optimization • Read, discuss, and build on the latest AI 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 To be successful in this role you have: • Drive to ship product improvements with production-quality, fully unit-tested code and rigorously-evaluated updates to models, prompts, context curation code, or other tunable system components • Solid grasp of LLM and agent evaluation fundamentals, especially for agent action trajectories, generated text, and non-uniform sampling regimes • Attention to detail and high standard of data quality for eval datasets • Thoughtfulness about API contracts and implications of exposing a platform feature to a given type of stakeholder or end user • Readiness to hit the ground running in a Mac development environment, programming in Python and/or Golang with the assistance of coding agents • Familiarity with industry standard agent architectures and large language models • Critical reading skill to catch subtle “miscommunication bugs” in English-language agent instructions • Ability to fix miscommunication bugs with precise writing and evals • Desire to move fast with a high degree of ownership • Drive to ship product improvements with production-grade code •