Staff Machine Learning Engineer, Agentic App Platform

ServiceNow offers an onsite opportunity in Mountain View, CA to scale and optimize a cutting-edge generative AI conversation engine for enterprise use. You’ll help build scalable product infrastructure and APIs while collaborating with ML, application, and product teams to deliver robust, domain-specific conversational experiences.

Responsibilities

• Build an extensive product infrastructure with intuitive interfaces that empower engineers and configurators to customize and optimize generative AI models, including data collection and feedback loops that adapt to diverse enterprise use cases.
• Deliver domain-specific conversational experiences tailored to varied business contexts.
• Design scalable API abstractions for the conversation platform that support popular chat clients such as MSTeams, Slack, and Web, while providing a neutral API for other parts of the engineering system.
• Optimize the dialog engine to support a wide range of features, leveraging private enterprise knowledge in the cloud, and enable real-time multilingual translation with a minimal memory footprint and low latency.
• Champion best practices in coding patterns, API design, scalability, robustness, and optimization, fostering a culture of excellence and continuous improvement among engineers.
• Provide comprehensive visibility into product performance through a robust logging and tracing framework, user-friendly debugging and triaging tools, and automated metrics for monitoring and analysis.
• Collaborate closely with ML engineers, application engineers, product teams, and customer support to drive feature development and scalability initiatives.

Requirements

• A strong foundation in computer science and software engineering with experience building scalable systems.
• Deep understanding of clean, modular, and scalable API design, with ability to promote high standards of code quality and craftsmanship.
• Passion for optimizing systems and performance, proficient in tracing, logging, and metrics frameworks, and a systematic approach to identifying and resolving latency, race conditions, and throughput bottlenecks.
• Ability to independently research new requirements and develop innovative solutions, thriving in fast-paced development and rapid iteration cycles.
• Strong communication skills to articulate rationale and design approaches, with cross-functional collaboration awareness to work effectively with multiple teams.
• Bachelor’s degree or higher in computer science or a related field.
• 7+ years of professional development experience building systems at scale.

Technologies

• MSTeams
• Slack
• Web