You'll design and build the infrastructure required to automatically validate and improve our platform and agents, including AI-powered agents for testing, evaluating, and automation of our systems that ensure our platform infrastructure and AI agents perform is reliable, repeatable, and effective at scale. Working closely with our AI Research, Security Research, and Engineering teams, among other things, you'll develop the infrastructure that enables rapid experimentation, deterministic validation, and continuous evaluation of autonomous AI attackers.
If you're excited about building developer platforms, testing infrastructure, and complex distributed systems in a fast-moving AI startup, we'd love to meet you.
Responsibilites
Design and build the testing and automation infrastructure that powers Tenzais platform and autonomous security agents. Define and shape the platform architecture for that goal.
Build deterministic and indeterministic validation tools for platform behavior and repeatable, data-driven evaluation for non-deterministic agent behavior.
Help develop continuous evaluation pipelines that measure performance, compare models and releases, detect regressions, and surface actionable results.
Build Python services and automation that orchestrate distributed test runs and manage their environments, inputs, and results.
Create internal tools and agents and CI/CD integrations that improve experimentation speed, developer productivity, and release confidence.
Partner with AI Research and Security Research to define evaluation methodologies, success criteria, and coverage.
Own systems end to end – from architecture and implementation through production reliability and continued evolution.
Contribute to technical design, architecture discussions, and code reviews across the engineering organization.
7+ years of software engineering experience, or equivalent depth demonstrated through the systems you have built and owned.
A strong track record of building and operating production backend automation systems, engineering infrastructure, or internal platforms.
Strong Python experience and the ability to design production-grade APIs, services, and distributed workloads.
Experience building testing frameworks, automation platforms, evaluation systems, or internal developer tooling.
A solid understanding of distributed systems, APIs, microservices, and cloud-native architectures, including concurrency, reliability, and failure modes.
Hands-on experience with CI/CD pipelines and modern software delivery practices.
The ability to take ambiguous technical problems, develop pragmatic solutions, and drive them through production.
High ownership, sound engineering judgment, and the ability to work independently in a fast-moving environment.
Clear communication skills and experience collaborating across research and engineering teams.
