Job Specifications
About The AI Security Institute
The AI Security Institute is the world's largest and best-funded team dedicated to understanding advanced AI risks and translating that knowledge into action. We're in the heart of the UK government with direct lines to No. 10, and we work with frontier developers and governments globally.
We're here because governments are critical for advanced AI going well, and UK AISI is uniquely positioned to mobilise them. With our resources, unique agility and international influence, this is the best place to shape both AI development and government action.
About The Team
Security Engineering at the AI Security Institute (AISI) exists to help our researchers move fast, safely. We are founding the Security Engineering team in a largely greenfield cloud environment, we treat security as a measurable, researcher centric product.
Secure by design platforms, automated governance, and intelligence led detection that protects our people, partners, models, and data. We work shoulder to shoulder with research units and core technology teams, and we optimise for enablement over gatekeeping, proportionate controls, low ego, and high ownership.
What You Might Work On
Help design and ship paved roads and secure defaults across our platform so researchers can build quickly and safely
Build provenance and integrity into the software supply chain (signing, attestation, artefact verification, reproducibility)
Support strengthened identity, segmentation, secrets, and key management to create a defensible foundation for evaluations at scale
Develop automated, evidence driven assurance mapped to relevant standards, reducing audit toil and improving signal
Create detections and response playbooks tailored to model evaluations and research workflows, and run exercises to validate them
Threat model new evaluation pipelines with research and core technology teams, fixing classes of issues at the platform layer
Assess third party services and hardware/software supply chains; introduce lightweight controls that raise the bar
Contribute to open standards and open source, and share lessons with the broader community where appropriate
If you want to build security that accelerates frontier scale AI safety research, and see your work land in production quickly, this is a good place to do it
Role Summary
Act as AISI's technical security lead for cloud and delivery infrastructure. You will enable secure-by-default platform patterns, provide reusable controls and guardrails, and partner with engineers to embed safe practices across the development lifecycle. You'll build influence through enablement, not enforcement. You will extend these patterns to AI/ML workloads, including secure handling of high-capability model weights, GPU estates, data/feature pipelines, evaluation/release gates, and inference services.
Responsibilities
Define and maintain secure-by-default IaC modules, bootstrap templates, and reference architectures
Provide consulting and coaching to platform and product teams to support secure delivery
Build tooling for identity, secrets, environment isolation, and pipeline hardening
Develop and maintain a baseline cloud control set (e.g. SCPs, logging, tagging)
Track and improve cloud posture with automated feedback loops
Lead or support post-incident reviews and design for resilience
Align technical controls with DSIT central governance and shared responsibility boundaries
Provide secure patterns for AI/ML training/finetuning and inference on AWS (e.g., EKS/ECS/SageMaker), including network isolation, egress controls, data locality, and private endpoints
Implement custody controls for model weights and sensitive datasets (encryption with KMS/HSM, least-privilege access paths, just-in-time/break-glass, tamper-evident logging)
Govern GPU/accelerator compute (quotas, tenancy/isolation, container image hardening, runtime policy, driver/AMI baselines)
Secure the AI supply chain: signed model/dataset artefacts, provenance/attestation (e.g., Sigstore/SLSA), model registries, and promotion gates tied to evaluation evidence
Establish paved paths for safe use of third-party model APIs (key management, egress allowlists, privacy-preserving logging, rate limiting, abuse and data exfil protection)
Embed safety guardrails and patterns for RAG and prompting (context isolation/sanitisation, prompt injection mitigations, output/content policies, human-in-the-loop hooks)
Deliver observability for AI surfaces (misuse/abuse telemetry, secrets/PII leak detection, anomalous output monitoring) integrated with incident response
Profile Requirements
Deep AWS experience, especially with security, identity, networking, and org-level services
Strong infra-as-code skills (Terraform, CDK, etc.) and CI/CD pipeline knowledge
Excellent technical judgment and stakeholder communication
Experience building influence in cross-functional environments
Practical understanding of AI/ML platform surfaces and risks (e.g., model weig