Senior Staff Machine Learning Engineer - Build Agent

ServiceNow•San Diego, CA

34d

About The Position

The Build Agent team is at the forefront of redefining AI-powered Application Development on ServiceNow—powering intelligent, AI-native experiences for developers, admins, and enterprise teams worldwide. Build Agent is ServiceNow's autonomous development agent designed to turn natural language into secure, production-ready enterprise applications. Build Agent isn't just another AI feature—it represents a fundamental shift in how developers and citizen builders create on the Now Platform. This conversational AI agent automates the complete development lifecycle: analyzing requirements from natural language, generating code and configuration, running automated tests, debugging errors, and deploying applications with built-in governance and security compliance. Build Agent is positioned to democratize application development while maintaining enterprise-grade quality and control. Our goal is to make building applications accessible, lightning-fast, and enjoyable.

Requirements

10+ years of related experience with a bachelor's degree; or 8 years and a master's degree; or a PhD with 5 years' experience; or equivalent work experience
Proficiency in prompt engineering, including techniques such as chain-of-thought, few-shot prompting, and prompt optimization strategies
Experience building production systems that integrate foundation models (e.g., Claude, GPT, Gemini) into customer-facing products
Expertise in writing efficient, well-structured, and maintainable code with strong practices around unit testing, profiling, and performance tuning
Familiarity with evaluation frameworks and methods for measuring LLM output quality, reliability, and cost-effectiveness
Knowledge of retrieval-augmented generation (RAG), agent architectures, or other patterns for extending model capabilities
Experience with code quality systems, static analysis, or CI/CD pipelines

Nice To Haves

Familiarity with agentic patterns such as tool use, planning, and self-correction loops
Experience with AI-assisted development tools such as Cursor, Windsurf, or similar
Understanding of security and governance considerations in AI-generated code
Familiarity with fine-tuning techniques (e.g., supervised fine-tuning, distillation) for understanding model behavior, even if not a primary job function
Background in AI/ML fundamentals that informs effective use of foundation models

Responsibilities

Design and develop scalable, maintainable systems that leverage foundation models through effective prompting strategies, orchestration, and tooling.
Collaborate with product managers to translate requirements into well-architected AI-powered solutions, owning features from prototyping through production deployment.
Contribute to the design and implementation of new AI-powered products and features while enhancing existing capabilities.
Build and refine prompt engineering workflows, evaluation frameworks, and retrieval systems to ensure consistent model performance and reliability.
Design and implement agentic workflows including multi-step task decomposition, tool use, and self-correction loops.
Integrate automated testing and evaluations into development workflows to measure output quality, latency, and cost across releases.
Participate in design and code reviews, ensuring best practices in system performance, maintainability, and testability.
Foster a culture of continuous learning and improvement by sharing best practices in AI engineering, prompt design, and quality evaluation.