Solve hard problems where AI meets cybersecurity.

What you'll work on

• Own stable, versioned platform APIs and SDKs, including client interfaces, compatibility rules, documentation, and examples.
• Build FastAPI services for enforcement decisions, evidence, policies, and red-team results.
• Design authentication, sessions, API keys, authorisation, and rigorous multi-tenant isolation.
• Build data and event interfaces, real-time streams, and a tamper-evident audit ledger.
• Create customer onboarding, policy integration, and operator dashboard workflows.
• Own testing and deployment across API compatibility, browser smoke tests, Cloud Run, and Cloud SQL.

What we're looking for

A product-minded platform engineer who makes complex systems clear and predictable and takes ownership from the data model to the customer integration.

• Strong backend experience with HTTP APIs; Python and FastAPI experience is preferred.
• Experience with observability, tracing, relational databases, and database migrations.
• Sound judgement around API design, versioning, SDKs, and compatibility.
• A strong understanding of authentication, authorisation, API keys, and multi-tenant access control.
• Good JavaScript and React skills for building operator-facing product surfaces.
• The ability to work independently and own technically uncertain customer problems.

What you'll work on

• Build and operate a low-latency runtime enforcement pipeline with predictable failure behaviour.
• Own observability and tracing across agent actions, tool calls, model calls, and enforcement decisions.
• Build tamper-evident evidence storage and enforce multi-tenant isolation throughout every data path.
• Create reliable event and streaming services with safe handling for load, retries, backpressure, and disconnections.
• Build infrastructure for red-team jobs, evaluation workloads, and model-serving services.
• Own cloud infrastructure, continuous delivery, secrets, artefact verification, and production trust boundaries.

What we're looking for

A systems engineer who reasons carefully about latency, failure, isolation, integrity, and cost, and uses measurements rather than assumptions.

• Strong experience with backend, distributed, or infrastructure systems; Python experience is preferred.
• Production observability and distributed tracing experience, ideally with OpenTelemetry or similar tooling.
• Experience building responsive services under load with robust timeout, retry, and backpressure behaviour.
• Experience with Postgres, Row-Level Security, migrations, and multi-tenant access-control testing.
• Hands-on experience with containers, cloud infrastructure, continuous delivery, and operational security.
• The ability to work independently and own technically ambiguous production problems.

What you'll work on

• Build the runtime classification stack that decides whether an agent's proposed action is authorised before it executes.
• Design action-boundary controls that allow, block, or redact sensitive data from flagged actions.
• Build evidence pipelines that record every AI action, verdict, and rationale.
• Compile natural-language company policies and regulation into executable runtime controls.
• Develop multimodal ingestion and detection across models, tools, and data types.
• Own systems end to end and ship them into real, high-consequence customer deployments.

What we're looking for

A technically exceptional builder who cares about getting AI safety and security right, and who grounds research in real-world impact.

• Typically 0-3 years of post-university experience building AI or machine learning systems.
• A strong foundation in computer science, machine learning, cybersecurity, or a related field.
• Evidence of exceptional building ability through production systems, research at a leading lab, startup work, or open source.
• A rigorous understanding of how AI systems fail and how adversaries can exploit them.
• The ability to move quickly, communicate clearly, and own complex technical problems independently.

What you'll work on

• Red-team production and pre-production agents across browser, code, enterprise, and multi-agent environments.
• Discover attacks involving prompt injection, goal manipulation, memory poisoning, tool abuse, identity, and data exfiltration.
• Develop realistic exploit chains across model, application, identity, tool, and infrastructure layers.
• Build automated attack agents, evaluation harnesses, and reusable security test suites.
• Turn research findings into detections, runtime evidence, policy controls, and product requirements.
• Assess customer deployments and communicate technically rigorous, actionable findings.

What we're looking for

An adversarial thinker with a builder's instinct who can move from an ambiguous attack hypothesis to a reproducible proof of concept.

• A strong foundation in security, computer science, machine learning, or a related field.
• Hands-on experience in offensive, application, cloud, product, or AI security.
• The ability to build security tooling and proof-of-concept exploits, ideally in Python and a systems language.
• Practical knowledge of modern agent architectures, including tool calling, retrieval, memory, orchestration, and permissions.
• Strong experimental discipline, clear communication, and ownership of technically ambiguous problems.