About the company
ServiceNow is the AI control tower for business reinvention. Our ServiceNow AI platform brings together any AI, any data, and any workflow—helping 85% of the Fortune 500® work smarter, faster, and better.
Responsibilities
- Design and build agentic systems: multi-agent orchestration with LangGraph/LangChain agents over frontier LLMs for transaction editing, conversational configuration, and multi-product quote planning.
- Own the Harness — our from-scratch agent execution runtime: full-duplex sessions, low-latency streaming, backpressure, live progress, partial results, graceful cancellation.
- Maintain MCP as a secondary interface for external interop.
- Implement A2A protocol for agent-to-agent task delegation and streaming.
- Engage in Forward Deployed Engineering: adapt the Harness and agents to real customer workflows.
- Work on RAG / context engineering: tenant-uploaded document ingestion, categorization, aggregation, prefix-cacheable prompt design.
- Apply classical ML when the problem calls for it.
Requirements
- Operating at a Senior-Staff bar in the agentic/LLM domain.
- Breadth across the stack: able to read a Spring Boot service, unblock frontend integration, reason about classical ML pipelines.
- Experience with state management, tool boundaries, streaming protocols, prompt/context architecture, multi-agent coordination.