Staff Software Engineer - AI Runtime

Remote (United States)

Job Details

Location: United States

Workplace: Remote

Employment Type: Full-Time

Schedule: PST or CST hours

Core Areas: AI agent infrastructure, API discovery, search and ranking, query planning, retrieval systems, agent orchestration, observability and evaluation, distributed query systems

Compensation: $192,000–$226,000 per year. The stated range includes base salary plus variable compensation, if applicable. Equity and benefits are also offered.

About the Role

This opportunity is for a Staff Software Engineer - AI Runtime focused on building early-stage infrastructure that enables AI agents to safely discover, understand, and interact with enterprise APIs. The role owns technically challenging problems across API discovery, schema understanding, search, ranking, relevance, query planning, and agent-to-API orchestration.

The position combines production software engineering with rapid R&D, algorithmic experimentation, agent orchestration, tool calling, retrieval quality, and evaluation. You will influence architecture and roadmap decisions while working with a small technical team and select enterprise customers to turn real usage patterns into scalable system improvements.

What You'll Do

• Design and build enterprise-scale systems for API discovery, schema understanding, and safe agent-to-API orchestration.
• Own search, ranking, relevance, and query-planning problems that determine how AI agents identify and use the appropriate APIs and data.
• Prototype rapidly, evaluate multiple algorithmic approaches, and iterate as new information from customer pilots changes technical priorities and direction.
• Build and evaluate agentic systems, including tool-calling frameworks, agent orchestration, and the observability and evaluation tooling required to understand and trust agent behavior.
• Work closely with a small, high-context engineering team where individual contributors have meaningful influence over architecture and technical direction.
• Engage with select enterprise customers to understand real-world usage patterns and incorporate those findings into system design.
• Communicate technical tradeoffs clearly to technical leadership and contribute directly to shaping the product and engineering roadmap.

Qualifications

• Hands-on production experience owning a search, ranking, relevance, or query-planning system at meaningful scale.
• Experience designing and iterating on the underlying logic of retrieval or ranking systems rather than only integrating third-party search tools.
• Experience evaluating multiple algorithmic approaches to difficult retrieval or ranking problems and explaining the associated tradeoffs.
• Ability to work effectively with ambiguous technical problems, define the right problem, and adapt when priorities change quickly.
• Strong written and verbal communication skills and comfort working in a small, fast-moving team with minimal process overhead.
• Growth mindset and strong interest in the intersection of AI agents and enterprise infrastructure.

Preferred Qualifications

• Production experience with Rust.
• Experience building agent orchestration systems, tool-calling frameworks, or agent evaluation and observability systems such as LLM-as-judge and tracing.
• Experience with RAG systems where you directly owned retrieval quality rather than only the integration layer.
• Background in distributed query engines, federated query planning, or database query optimization.

Benefits

• Equity participation.
• Choice of three medical plans for U.S. employees.
• California residents may choose from two additional medical plan options.
• Dental and vision benefits.
• The position can be performed remotely from anywhere in the United States while working PST or CST hours.
• Employment eligibility is verified through E-Verify using Form I-9 information for U.S. hires.