This is a fully remote position, open to applicants in Australia.

📋 Description

• Develop and enhance Nullify's multi-provider agent runtime, incorporating loops, structured output, budget governance, and checkpoint/resume capabilities for extended operations.

• Create agents that analyze business logic and real application behaviors instead of merely matching predefined signatures.

• Expand and maintain the evaluation harness by integrating labeled test cases, scoring mechanisms, and regression tracking.

• Take full ownership of agents throughout the entire process, including detection, validation, fix generation, and making critical judgment calls.

⛳️ Requirements

• Strong foundation in software engineering — proficient in Go or Python, with experience in production environments, not limited to notebooks.

• Proven experience in developing or managing LLM-based agents that go beyond simple prompt-response interactions: including tool usage, multi-step reasoning, retries, and evaluations.

• A scientific approach to measuring the effectiveness of solutions before deployment.

• A genuine interest in security with a commitment to enhancing knowledge in the field.