AI Agent Runtime Engineer

Sierra; San Francisco (CA); On-site; USD 140,000 - 190,000; Full time

Benefits offered by this job

Flexible (unlimited) paid time off

Medical, dental, and vision benefits

Life insurance and disability benefits

Retirement plan dependent on country

Parental leave

Fertility and family building benefits

Lunch and snacks

Discretionary benefit stipend

Free alphorn lessons

Job summary

Sierra in San Francisco is building a platform to enable every company in the world to build better, more human customer experiences with AI. You will work on the Agent SDK — the orchestration engine, runtime, and primitives that define how agents reason, take actions, and interact with users and systems.

You’ll design steerable, verifiable primitives, improve retrieval and grounding for trustworthy responses, and build evaluation frameworks to measure and improve agent quality over time.

Qualifications

• 4+ years hands-on experience building production products and systems.
• Strong software engineering fundamentals and production systems
• Degree in Computer Science or related field, or equivalent professional experience.
• Experience with building AI-powered systems or agent frameworks is a plus.

Responsibilities

• Build core systems powering agents and the Agent SDK.
• Design steerable and verifiable agent primitives.
• Improve retrieval and grounding for trustworthy responses.
• Build evaluation frameworks to measure and improve agent quality.

Skills

Strong software engineering

High agency

Production systems

4+ years experience

Education

Bachelor's in CS or related

Tools

Go

TypeScript

Agent SDK

Job description

Sierra in San Francisco is building a platform to enable every company in the world to build better, more human customer experiences with AI. You will work on the Agent SDK — the orchestration engine, runtime, and primitives that define how agents reason, take actions, and interact with users and systems.

You’ll design steerable, verifiable primitives, improve retrieval and grounding for trustworthy responses, and build evaluation frameworks to measure and improve agent quality over time.