Staff AI Engineer — Conversational Agentic AI

ServiceNow; Santa Clara (CA); On-site; USD 176,100 - 308,200; Full time

Benefits offered by this job

Health plans

401(k) Plan with company match

Flexible time away plan

Family leave programs

Job summary

ServiceNow is looking for a Staff AI Engineer to join our Agent Orchestration team in Santa Clara, California. You'll own parts of our agent execution harness and be responsible for ensuring the infrastructure supports enterprise AI at scale.

The ideal candidate has over 7 years of experience, hands-on with generative AI products, deeply understands large language models, and excels in prompt engineering and evaluation frameworks. This role offers a competitive salary and comprehensive benefits.

Qualifications

• 7+ years of experience in building production software systems.
• Hands-on experience in shipping generative AI products.
• Solid understanding of large language models and their behavior.
• Practical experience in designing and evaluating prompts.
• Experience in eval engineering and quality decision making.
• Cost and efficiency awareness at the system level.
• Strong software engineering fundamentals in distributed systems.

Responsibilities

• Own significant parts of the agent harness infrastructure.
• Design and build the agent execution harness and orchestration layer.
• Own the runtime’s fault tolerance, latency, and throughput.
• Instrument harness with tracing, cost attribution, and visibility.
• Build prompt management systems for stable agent behavior.
• Design evaluation frameworks for agent quality and decision making.
• Integrate with frontier LLMs for production optimization.
• Set technical standards and coach team members.

Skills

Reliability

Performance

Scalability

Prompt engineering

Eval engineering

Software engineering fundamentals

Tools

AI observability tooling

Cloud-native infrastructure

Job description

ServiceNow is looking for a Staff AI Engineer to join our Agent Orchestration team in Santa Clara, California. You'll own parts of our agent execution harness and be responsible for ensuring the infrastructure supports enterprise AI at scale.

The ideal candidate has over 7 years of experience, hands-on with generative AI products, deeply understands large language models, and excels in prompt engineering and evaluation frameworks. This role offers a competitive salary and comprehensive benefits.