AI Agent Runtime Engineer — Remote, Equity

Big Wombat LLC; United States; Remote; USD 215,000 - 325,000; Full time

Benefits offered by this job

Equity

Remote work (US/EU time zones)

Job summary

Big Wombat LLC is seeking a hands-on software engineer to build the agent infrastructure that powers dependable language-model driven agents. You will own the runtime, memory, retrieval, and permissions aspects across long-running tasks, with ownership of reliability and auditability.

The role is full-time and remote within US or EU time zones, offering a base salary of 215,000–325,000 USD with equity. You will collaborate across components to ensure secure, extensible runtimes for agents.

Qualifications

• Hands-on software engineering role building agent infrastructure.
• Ability to design reliable systems that handle retries, failures, and long running execution.
• Interest or experience in language model agents, tool use, retrieval, or extensible runtimes.
• Sound judgment around permissions, credentials, user approval, and auditability.
• Ability to take ownership of technical problems across multiple areas of the product.

Responsibilities

• Build the agent runtime, including task dispatch, tool calls, execution state, retries, cancellation, and error handling.
• Design an extension system that lets users, field engineers, and agents adapt the harness to practical needs.
• Define how agents store learned information with provenance, confidence, and a way to handle changing or stale facts.
• Support coordination among agents through concurrent work, partial failures, retries, and restarts.
• Develop local retrieval for personal documents and messages, keeping context current and responsive on a user’s device.
• Implement model routing and trust controls, including provider fallback, sandboxing, permissions, and auditable actions.

Job description

Big Wombat LLC is seeking a hands-on software engineer to build the agent infrastructure that powers dependable language-model driven agents. You will own the runtime, memory, retrieval, and permissions aspects across long-running tasks, with ownership of reliability and auditability.

The role is full-time and remote within US or EU time zones, offering a base salary of 215,000–325,000 USD with equity. You will collaborate across components to ensure secure, extensible runtimes for agents.