SlipstreamJobs tracks this role from the company's public career site. Apply directly on the employer's site.
Salary: USD 176,100 - 308,200 / annual
ServiceNow's Agentic Engineering organization is building conversational AI that transforms enterprise intent into completed work. The Agent Orchestration team owns the execution core—agent harness, orchestration runtime, multi-agent coordination, memory management, and evaluation frameworks that ensure agents behave correctly in production.
As a Staff Machine Learning Engineer, you will own significant parts of the agent harness, the infrastructure layer enabling AI agents to reason over enterprise data, take action across workflows, and run safely at Fortune 500 scale.
Key responsibilities include:
• Harness Engineering: Design and build the agent execution harness—the orchestration layer that routes inputs, manages context, invokes tools, handles retries, and surfaces execution state across multi-step agentic workflows.
• Reliability at Scale: Own the runtime's fault tolerance, latency, and throughput; design for enterprise workflows that cannot fail silently or unpredictably.
• Observability: Instrument the harness with tracing, cost attribution, and latency visibility so the team can reason about agent behavior in production and catch failures before customers do.
• Prompt Infrastructure: Build prompt management systems—versioning, templating, and systematic evaluation—that keep agent behavior stable across model updates and configuration changes.
• Eval Engineering: Design and own evaluation frameworks (unit evals, integration evals, production monitors) that measure agent quality, catch regressions, and drive data-informed decisions.
• LLM Integration: Integrate with and abstract over frontier LLMs, managing model routing, fallback strategies, cost, and latency trade-offs in production.
• Technical Leadership: Set technical standards through architecture decisions, code reviews, and coaching—particularly on agentic design patterns and production AI discipline.
• System Boundary Design: Define where agent logic lives—what's a tool call, a sub-agent, a hardcoded path, or a human escalation—and establish those design standards across the team.
You'll operate in a fast-moving, startup-like AI product environment backed by ServiceNow's global scale, working on autonomous systems (Otto) that power enterprise automation across the Fortune 500.
Requirements:
• 7+ years building production software systems with strong track record on reliability, performance, and scalability
• Hands-on experience shipping generative AI products—not just integrating LLM APIs or building prototypes, but owning AI-powered features that production users depend on
• Solid depth in how large language models work: failure modes, context constraints, and how prompt design shapes model behavior at scale
• Python; experience with SageMaker, Vertex AI, AzureML, or Kubeflow; SQL
• Practical prompt engineering experience: systematically designing, versioning, and evaluating prompts across model updates or A/B evaluation cycles
• Real track record in eval engineering—not just familiarity, but a portfolio of evaluation suites designed, shipped, and used to drive quality decisions in production AI systems
• Cost and efficiency awareness at the system level: experience reasoning about model routing, inference cost, and latency tradeoffs in production
• Strong software engineering fundamentals: distributed systems, API design, and testing discipline
• Comfort operating in fast-moving, ambiguous, startup-like AI product environments
Nice to Have:
• Experience with multi-agent coordination patterns (A2A, MCP)
• Familiarity with agent frameworks (LangChain, LlamaIndex, or similar)
• Prior experience shipping AI systems in enterprise software
• Experience with AI observability tooling (tracing, cost tracking, LLM-specific monitoring)
• Familiarity with cloud-native infrastructure, service observability, logging, monitoring, reliability engineering, and production troubleshooting
