ServiceNow Global Cloud Services OODP (Observability and Ops Data Platform) Team is looking to lead the design and engineering of next-generation AI agentic workflows in their observability products.
Requirements
- Proven experience designing and deploying LLM-powered workflows or AI agents in production environments.
- Strong expertise in agentic AI orchestration frameworks and familiarity with planner-executor and multi-agent architectures.
- Strong Java, Python and REST API, backed by strong computer science fundamentals in data structures, algorithms, and software design.
- Strong data background with RDBMS and TSDB, and proficiency in analytical SQL and PromQL queries.
- Expertise in CI/CD pipelines, containerization (Kubernetes, Docker), and cloud-native deployment for AI-driven services.
- Excellent troubleshooting, debugging, and performance optimization skills for complex workflows and distributed agents.
- Strong statistical background with ability to design scalable, robust, and efficient ML systems that integrate with the full tech stack.
Responsibilities
- Lead the design and development of agentic workflows that leverage LLMs and autonomous agents to automate complex, multi-step business processes.
- Architect and implement AI agent frameworks to orchestrate planning, tool use, and collaboration across systems.
- Define, standardize, and maintain reusable workflow components (retrieval modules, planners, memory, state machines, execution engines).
- Build integrations with observability platforms, APIs, and other data sources.
- Apply RAG (Retrieval-Augmented Generation), structured knowledge grounding, and guardrails to ensure accuracy and reliability of AI-driven workflows.
- Establish best practices for end-to-end development, including design, implementation, testing, CI/CD automation, monitoring, and logging of agentic workflows.
- Partner with research and data science teams to evaluate LLM models, optimize prompting strategies, and measure workflow efficiency, reliability, and trust.
Other
- Experience in leveraging or critically thinking about how to integrate AI into work processes, decision-making, or problem-solving.
- Collaborate with UX engineers, product managers, and domain experts to ensure workflows are human-centered, safe, and transparent.
- Mentor engineering teams in agentic workflow design patterns and share expertise in LLM orchestration at scale.
- Strong collaboration and cross-functional communication skills to work with UX, product, and AI research teams.
- Preferred: Familiarity with responsible AI principles (bias mitigation, safety, transparency) and monitoring tools for AI/agentic workflows.
