Nullify is building the post-human product security program - one harness that drives product security work to closure by continuously allocating AI capacity toward the highest-impact work.
Building that harness means more than building agents that work in the abstract. They need to perform reliably inside real enterprise environments, across different codebases, architectures, security programs and engineering constraints.
You'll work closely with some of our largest customers and own how Nullify's agents perform in their environment. Where agents encounter failure modes or edge cases when discovering, triaging or remediating vulnerabilities, you'll diagnose them and improve the system - whether that means improving reasoning, context, tools, evaluation, orchestration or the underlying product.
The goal is to turn what we learn from each customer into a stronger harness. As edge cases become product, each FDE supports more customers and the system requires less human intervention.
What you'll do
- Own the performance of Nullify's agents across a set of large enterprise customers.
- Find where agents and subagents fail, underperform or require human intervention - and engineer those weaknesses out.
- Work against real customer codebases and environments to understand failure modes that don't show up in a benchmark.
- Build and improve agent tooling, context, orchestration, evaluation and underlying product capabilities.
- Turn customer-specific edge cases into generalized capabilities in the harness.
- Work directly with customer security and engineering teams to understand what good performance actually looks like in their environment.
- Feed what you learn in the field directly into the core product, increasing how many customers the harness can serve autonomously.
What you'll bring
- Strong fundamentals in Go and/or Python, and the judgment to know when to reach for which.
- Experience with production distributed systems - queues, state machines, idempotency, failure modes.
- A preference for simple, correct code over clever abstractions.
- Background in pentesting, CTFs, bug hunting and security engineering preferred but not required
- Curiosity about security, even if it's not your background yet.
- Customer obsession and passion for servicing customers and making them successful
Compensation
- USD120,000-180,000 + equity + benefits
