Job Description
n
We're building the agent runtime that finds, validates, and prepares fixes for vulnerabilities automatically, while people retain judgment and merge control. That means solving real distributed-systems and reasoning problems, not gluing together prompts.
What you'll do n
n
n
Build and harden Nullify's multi-provider agent runtime — turn loops, structured output, budget governance, checkpoint/resume for multi-hour runs.
n
n
Design agents that reason about business logic and real application behavior, not just pattern-match against known signatures.
n
n
Build and grow our evaluation harness — labelled test cases, scoring, regression tracking — so we can measure whether an agent got better or just got different.
n
n
Own agents end-to-end: detection, validation,



fix generation, and the judgment calls in between.
n
What you bring n
n
n
Robust software engineering fundamentals — Go or Python, comfortable in production systems, not just notebooks.
n
n
Experience building or operating LLM-based agents beyond a single prompt-response call: tool use, multi-step reasoning, retries, evals.
n
n
A scientist's instinct for measuring whether something actually works before shipping it.
n
n
Genuine interest in security — you don't need to be an expert yet, but you need to want to become one.
n
n

📌 A.I. Engineer - Nullify (New South Wales)
🏢 Black Nova Portfolio
📍 New South Wales