---
title: 'Technical Programme Manager - Model Transparency at AI Security Institute'
canonical: 'https://feeny.ai/job/technical-programme-manager-model-transparency-ai-security-institute-london-sy2vvq2d7y5w'
type: 'job'
last_seen: '2026-10-16'
---

# Technical Programme Manager - Model Transparency at AI Security Institute

- **Company:** AI Security Institute
- **Location:** London, United Kingdom
- **Posted:** 2026-10-13
- **Last confirmed live:** 2026-10-16
- **Apply:** https://job-boards.eu.greenhouse.io/aisi/jobs/4997713101

## Job description

## 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 (the Prime Minister's office), 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.

The deadline for applying to this role is Sunday 1st November, end of day, anywhere on Earth.

## About the role

AISI aims to turn progress on important research questions in AI security into real insight and impact for our partners and the public. This requires running research programmes that actually deliver, and making these programmes rigorous and fast is its own discipline. The AI Security Institute is hiring a Technical Programme Manager for our Model Transparency team to do exactly this.

Over the next twelve months, this team will need to move faster, deliver more complex research programmes and evaluations, and engage more deeply with partners in major AI labs and across government than ever before.

Technical Programme Managers make this work possible. You will work directly with the team's researchers and engineers to turn vast research questions into tractable programmes. You will be held responsible for ensuring our research stands up to rigorous empirical standards to inform policy, recommending which technical work needs to happen, and untangling knotty dependencies across workstreams.

## About the team

The ability to effectively evaluate and monitor AI systems will grow in importance as models become more capable, autonomous, and integrated into society. If models can detect and game evaluations, obscure their reasoning, or behave differently under observation, the safety claims that governments and developers rely on become unreliable.Understanding and addressing these risks is essential to ensuring that oversight of advanced AI systems keeps pace with their capabilities.

The Model Transparency team is a research team within AISI focused on ensuring that evaluations, assessments, and monitoring of frontier AI systems remain reliable as models become less transparent. We research how and why oversight is declining – through phenomena such as evaluation awareness, unfaithful chain-of-thought reasoning, and changes in model architectures – and develop methods (including white and black box methods) to detect, measure, and mitigate potential issues. We share our findings with frontier AI companies (including Anthropic, OpenAI, DeepMind), UK government officials, and allied governments, and publicly to inform their deployment, research, and policy decisions. We also work directly with safety teams at frontier labs, contributing to safety case reviews and helping improve their alignment evaluation methodology.

Our recent work includes [the loss of oversight report](https://www.aisi.gov.uk/research/loss-of-oversight-how-ai-systems-may-become-harder-to-audit-monitor-and-investigate), [auditing games for sandbagging](https://www.alignmentforum.org/posts/2ANCyejqxfqK2obEj/some-natural-emergent-misalignment-from-reward-hacking-in), [reproducing natural emergent misalignment from reward hacking](https://www.alignmentforum.org/posts/2ANCyejqxfqK2obEj/some-natural-emergent-misalignment-from-reward-hacking-in), and [identifying open-weight language models that game propensity evaluations](https://www.lesswrong.com/posts/GrEvutegoJFeTkzwe/we-found-an-open-weight-model-that-games-alignment-honeypots-1).

## What you will own

Programme architecture. You will work directly with your team's technical staff to set the scope of projects: refining what questions we're actually trying to answer, what the milestones and success criteria are for technical work, and how to sequence dependencies, resource, and time across the team. You will turn "we should probably look into X" into a tractable plan with clear deliverables, without imposing process that gets in the team's way. You must be comfortable with ambiguity: you will be immersed in a fast-moving environment and won’t always have a settled roadmap. .

Delivery tracking and unblocking. You will spot and solve problems so that the team's delivery continually improves, and own tracking progress to create visibility and establish control without overhead. You will surface technical blockers before they become crises, intervene directly to resolve them, and know exactly when and to whom to escalate. The goal is the team spending their time on the work, not logistics.

Cross-government technical engagement. You will speak with government partners on a technical level and be a trusted representative and ambassador for good relationships with them.

Team operations and pace. You will determine the operational rhythm that lets a small, high-performing team inside government move at the speed of billion-dollar AI companies. You will ensure the team has what it needs to deliver and be unfussy about doing whatever needs to be done to unblock things and prevent them from falling through the cracks.

## Role Requirements

- A track record working with technical colleagues. You have delivered technical programmes in a similarly high-ambiguity environment. You know how to scope and structure open-ended goals (not just deliver against a pre-defined plan). You have earned the trust of technical teams by understanding their work deeply enough to provide critical challenge and engage beyond process.
- Comfort operating at the frontier of AI. You do not need to be a machine learning researcher, but you need to be fluent enough in frontier AI to operate in constant conversation with technical staff about our work, strategy, and research taste; you should have your own taste on what's hard, what's speculative, what's blocked, and what "good" looks like for a given experiment or evaluation.
- High agency and ownership. You take responsibility for outcomes, not activities. When something is stuck, you pick up the phone. You do not wait for someone else to escalate.
- Credibility with technical teams. Researchers trust you because you understand their work, respect their constraints, and demonstrably make their lives easier. You influence through competence and service, not authority or process.
- Strong prioritisation under pressure. You can identify what actually matters on a daily, weekly, monthly, and quarterly level and focus the team's energy. You have the judgement to recognise work that isn't landing and the confidence to recommend that it stop.
- Discretion and judgement in a sensitive domain. You understand that the work we do often carries sensitivity.

Strong candidates may also have:

- Existing security clearances.
- Fluency in, or eagerness to adopt, modern productivity tools (coding agents, Linear, Slack) and willingness to use AI tools as part of daily work.

Selection process

Applications are reviewed on a rolling basis. We encourage you to apply early.

- Application - CV and a short cover note (max 500 words) explaining what draws you to this role and what you would bring. Please also indicate which team you would prefer to join.
- Screening interview - Lightweight conversation on trajectory, motivation and fit.
- Work test - A take-home exercise designed to test programme management judgement in context. You will receive this after the screening interview.
- Technical interview - Discussion of your work test.
- Behavioural interview - Deeper dive on stakeholder management, prioritisation and team dynamics.
- Senior leadership interview (30 min) - Final conversation with AISI senior leadership.

Security Clearance

Appointment is conditional on successfully completing UK Government SC clearance. Prior clearance is not required—we will sponsor and support you. You should normally have been resident in the UK for the past 5 years. More detail on clearance eligibility can be found on the UK Government website: [National security vetting: clearance levels - GOV.UK.](https://www.gov.uk/government/publications/united-kingdom-security-vetting-clearance-levels/national-security-vetting-clearance-levels)

## What We Offer

Impact you couldn't have anywhere else

- Incredibly talented, mission-driven and supportive colleagues.
- Direct influence on how frontier AI is governed and deployed globally.
- Work with the Prime Minister’s AI Advisor and leading AI companies.
- Opportunity to shape the first & best-resourced public-interest research team focused on AI security.

Resources & access

- Pre-release access to multiple frontier models and ample compute.
- Extensive operational support so you can focus on research and ship quickly.
- Work with experts across national security, policy, AI research and adjacent sciences.

Growth & autonomy

- If you’re talented and driven, you’ll own important problems early.
- 5 days off and annual stipends for learning and development, and funding for conferences and external collaborations.
- Freedom to pursue research bets without product pressure.
- Opportunities to publish and collaborate externally.

Life & family*

- Modern central London office, or where applicable, option to work in similar government offices in Birmingham, Cardiff, Darlington, Edinburgh, Salford or Bristol.
- Hybrid working, flexibility for occasional remote work abroad and stipends for work-from-home equipment.
- At least 25 days’ annual leave, 8 public holidays, extra team-wide breaks and 3 days off for volunteering.
- Generous paid parental leave (36 weeks of UK statutory leave shared between parents + 3 extra paid weeks + option for additional unpaid time).
- On top of your salary, we contribute 28.97% of your base salary to your pension.
- Discounts and benefits for cycling to work, donations and retail/gyms.

*These benefits apply to direct employees. Benefits may differ for individuals joining through other employment arrangements such as secondments.

Salary

Annual salary is benchmarked to role scope and relevant experience. Most offers land between £65,000 and £145,000 made up of a base salary plus a technical allowance (take-home salary = base + technical allowance). An additional 28.97% employer pension contribution is paid on the base salary.

This role sits outside of the [DDaT pay framework](https://ddat-capability-framework.service.gov.uk/) given the scope of this role requires in depth technical expertise in frontier AI safety, robustness and advanced AI architectures.

The full range of salaries are available below:

- Level 3: £65,000–£75,000 (Base £40,850 + Technical Allowance £24,150–£34,150)
- Level 4: £85,000–£95,000 (Base £48,540 + Technical Allowance £36,460–£46,460)
- Level 5: £105,000–£115,000 (Base £63,165 + Technical Allowance £41,835–£51,835)
- Level 6: £125,000–£135,000 (Base £76,475 + Technical Allowance £48,525–£58,525)
- Level 7: £145,000 (Base £76,475 + Technical Allowance £68,525)

Additional Information

Use of AI in Applications

Artificial Intelligence can be a useful tool to support your application, however, all examples and statements provided must be truthful, factually accurate and taken directly from your own experience. Where plagiarism has been identified (presenting the ideas and experiences of others, or generated by artificial intelligence, as your own) applications may be withdrawn and internal candidates may be subject to disciplinary action. Please see our [candidate guidance](https://eur02.safelinks.protection.outlook.com/?url=https%3A%2F%2Fwww.civil-service-careers.gov.uk%2Fartificial-intelligence-and-recruitment%2F&data=05%7C02%7CLynn.Tan%40dsit.gov.uk%7Ccf5d753b7f19427afc8f08de4c307014%7Ccbac700502c143ebb497e6492d1b2dd8%7C0%7C0%7C639031968075235036%7CUnknown%7CTWFpbGZsb3d8eyJFbXB0eU1hcGkiOnRydWUsIlYiOiIwLjAuMDAwMCIsIlAiOiJXaW4zMiIsIkFOIjoiTWFpbCIsIldUIjoyfQ%3D%3D%7C0%7C%7C%7C&sdata=jCrYoy62YfXN%2FLIB%2FhtHxdLGbCOgropbkZXDyQsUMC4%3D&reserved=0)for more information on appropriate and inappropriate use.

Use of AI tools in recruitment

We may use AI tools to help our hiring team review applications, for example by summarising application materials and helping us prioritise them against the published criteria. We do not use AI tools to find information about you from other sources, including online. People make every decision. We do not make solely automated decisions about candidates. Find out more, including your rights, in our recruitment privacy notice: https://www.aisi.gov.uk/careers/privacy-policy.

Internal Fraud Database

The Internal Fraud function of the Fraud, Error, Debt and Grants Function at the Cabinet Office processes details of civil servants who have been dismissed for committing internal fraud, or who would have been dismissed had they not resigned. The Cabinet Office receives the details from participating government organisations of civil servants who have been dismissed, or who would have been dismissed had they not resigned, for internal fraud. In instances such as this, civil servants are then banned for 5 years from further employment in the civil service. The Cabinet Office then processes this data and discloses a limited dataset back to DLUHC as a participating government organisations. DLUHC then carry out the pre employment checks so as to detect instances where known fraudsters are attempting to reapply for roles in the civil service. In this way, the policy is ensured and the repetition of internal fraud is prevented.  For more information please see - [Internal Fraud Register.](https://www.gov.uk/government/publications/internal-fraud-register-privacy-notice/internal-fraud-register-privacy-notice)

Security

Successful candidates must undergo a criminal record check and get https://www.gov.uk/government/publications/government-baseline-personnel-security-standard before they can be appointed. Additionally, there is a strong preference for eligibility for https://www.gov.uk/government/publications/national-security-vetting-advice-for-people-who-are-being-vetted. Some roles may require higher levels of clearance, and we will state this by exception in the job advertisement. [See our vetting charter here.](https://www.gov.uk/government/publications/vetting-explained-and-our-vetting-charter/the-vetting-charter)

Nationality requirements

We may be able to offer roles to applicant from any nationality or background. As such we encourage you to apply even if you do not meet the standard https://www.gov.uk/government/publications/nationality-rules

Working for the Civil Service

The http://civilservicecommission.independent.gov.uk/code/ sets out the standards of behaviour expected of civil servants. The Civil Service embraces diversity and promotes equal opportunities. As such, we run a Disability Confident Scheme (DCS) for candidates with disabilities who meet the minimum selection criteria. The Civil Service also offers a Redeployment Interview Scheme to civil servants who are at risk of redundancy, and who meet the minimum requirements for the advertised vacancy.

Diversity and Inclusion

The Civil Service is committed to attract, retain and invest in talent wherever it is found. To learn more please see the https://www.gov.uk/government/publications/civil-service-people-plan-2024-2027/civil-service-people-plan-2024-2027-html and the https://www.gov.uk/government/publications/civil-service-diversity-and-inclusion-strategy-2022-to-2025. As part of the application process, we monitor statistics on D&I. You can see how we process this data here: [Recruitment privacy notice - GOV.UK](https://www.gov.uk/government/publications/government-digital-service-recruitment-privacy-notice/recruitment-privacy-notice).

## About AI Security Institute

## Company Overview
- **One-liner**: The AI Security Institute (AISI) is the UK government’s in-house research organisation dedicated to understanding and mitigating risks from advanced AI, equipping policymakers with scientific evidence to keep the public safe.
- **Entity Type**: Government Research Institute (part of the UK Department for Science, Innovation and Technology)
- **Headquarters**: London, UK (with satellite offices in Birmingham, Cardiff, Darlington, Edinburgh, Salford, and Bristol)
- **Founded**: 2023 (launched as the Frontier AI Taskforce at the Bletchley Park AI Safety Summit, later renamed AISI)
- **Founders**: Not applicable (government entity); key leadership includes Interim Director Adam Beaumont (former GCHQ Chief AI Officer), CTO Jade Leung (former OpenAI Governance lead, also PM’s AI Advisor), Chief Scientist Geoffrey Irving, and Chair Ian Hogarth.

## Core Business
- **Primary industry**: AI safety and security research, public policy, technical evaluation of frontier AI models.
- **Target customers**: UK and allied governments, AI developers (OpenAI, Google DeepMind, etc.), the broader research community, and the general public.
- **Mission**: “Equip governments with a scientific understanding of the risks posed by advanced AI.”

## Products & Services
- **Pre‑deployment Evaluations**: Rigorous testing of leading AI systems before public release, including assessments of cyber misuse, safeguards, alignment, and autonomy. [aisi.gov.uk](https://www.aisi.gov.uk/)
- **Open‑Source Tools (e.g., Inspect)**: Evaluation frameworks released publicly so the wider research community can build on AISI’s work. [aisi.gov.uk](https://www.aisi.gov.uk/about)
- **Grant Programme**: >£15 million in grants to accelerate global research into AI risk mitigations. [aisi.gov.uk](https://www.aisi.gov.uk/about)
- **Policy Advisory & International Collaboration**: Informing UK and allied governments, shaping global AI governance, and sharing findings with partners. [aisi.gov.uk](https://www.aisi.gov.uk/about)

## Market Standing
- **Valuation / Market Cap**: Not applicable (government‑funded entity)
- **Key Metric**: £66 million in funding per financial year; >100 technical staff; priority access to >£1.5 billion of compute via the UK’s AI Research Resource. [aisi.gov.uk](https://www.aisi.gov.uk/about)
- **Notable Investors / Partners**: UK Government (No. 10, DSIT); collaborations with OpenAI, Google DeepMind, University of Oxford; advisory board includes Yoshua Bengio. [aisi.gov.uk](https://www.aisi.gov.uk/about)
- **Growth Signals**: Rapid scaling from a taskforce to a permanent institute; senior hires from OpenAI, DeepMind, and Oxford; published Frontier AI Trends Report and a comprehensive Research Agenda. [aisi.gov.uk](https://www.aisi.gov.uk/research-agenda)

## Competitive Advantages
- **Unique position within government**: Combines the authority and resources of the state with the agility and expertise of a startup.
- **Pre‑release model access**: Privileged, pre‑deployment access to the most advanced frontier AI models.
- **Substantial compute & funding**: Backed by £66M/year and exascale supercomputing resources.
- **Talent density**: Over 100 technical staff from top industry, academic, and national‑security backgrounds.
- **Global influence**: Directly shapes UK and allied AI policy, with a seat at the table for international AI safety governance.

## Strategic Focus
- **Deepen scientific understanding of frontier AI risks**: Focus on evaluations of cyber misuse, alignment, control, autonomy, human influence, and societal resilience.
- **Build evaluation infrastructure**: Continue developing open‑source tools (e.g., Inspect) and scaling in‑house research.
- **Influence global policy**: Work with AI developers and governments to embed safety mitigations and shape international norms.
- **Expand research partnerships**: Mobilise >£15M in grants and collaborate with external labs to accelerate breakthroughs.

## Why Work Here
- **Mission‑driven impact**: Direct influence on how frontier AI is governed and deployed globally.
- **Hybrid working**: Modern central London office (with cafes, food court, gym) or option to work in other UK government hubs; flexibility for occasional remote work abroad.
- **Generous benefits**: 28.97% employer pension contribution, at least 25 days annual leave + 8 public holidays + 3 volunteering days, 36 weeks statutory shared parental leave + 3 extra paid weeks.
- **Growth & autonomy**: Own important problems early; 5 days learning & development leave, annual stipends, conference funding; freedom to publish and collaborate externally.
- **Top‑tier resources**: Pre‑release access to multiple frontier models, ample compute, and operational support to ship quickly.
- **Culture**: Highly collaborative, ambitious, pragmatic, and mission‑first; described as “incredibly talented, mission‑driven and supportive colleagues.” [aisi.gov.uk](https://www.aisi.gov.uk/careers)
- **Visa sponsorship**: Available for technical roles; non‑technical roles have UK civil service nationality requirements. [aisi.gov.uk](https://www.aisi.gov.uk/careers)

## Sources
1. [aisi.gov.uk](https://www.aisi.gov.uk/) – Homepage with mission, impact, and research overview.
2. [aisi.gov.uk/about](https://www.aisi.gov.uk/about) – Detailed organisation description, leadership, funding, and research areas.
3. [aisi.gov.uk/careers](https://www.aisi.gov.uk/careers) – Career page with benefits, working patterns, and application process.
4. [greenhouse.io/aisi](http://job-boards.greenhouse.io/aisi) – Current open roles (Research Scientist, Security Engineer, Software Engineer, etc.).
5. [aisi.gov.uk/research-agenda](https://www.aisi.gov.uk/research-agenda) – Formal research agenda outlining priorities.

## Other roles at AI Security Institute

- [Expression of Interest - Core Technology Team](https://feeny.ai/job/expression-of-interest-core-technology-team-ai-security-institute-london-8j763yrvh297) — London, United Kingdom
- [Expression of Interest - Research Director](https://feeny.ai/job/expression-of-interest-research-director-ai-security-institute-london-2jjfk0wb14pt) — London, United Kingdom
- [Alignment Red Team - Research Engineer/Research Scientist](https://feeny.ai/job/alignment-red-team-research-engineer-research-scientist-ai-security-institute-vvpbs1qmed3m) — London, United Kingdom
- [Engineering Lead - Human Influence](https://feeny.ai/job/engineering-lead-human-influence-ai-security-institute-london-x5htgaksjj8e) — London, United Kingdom
- [Expression of Interest: Next-generation Agentic Controls and Forensics (Technical Roles)](https://feeny.ai/job/expression-of-interest-next-generation-agentic-controls-and-forensics-technical-ctscsak21fwk) — London, United Kingdom
- [Expression of Interest- Cyber & Autonomous Systems Team](https://feeny.ai/job/expression-of-interest-cyber-autonomous-systems-team-ai-security-institute-82jdz2f84ss7) — London, United Kingdom
- [Expression of Interest- Chem Bio](https://feeny.ai/job/expression-of-interest-chem-bio-ai-security-institute-london-gp5ec2nckedp) — London, United Kingdom
- [Senior Software Engineer, Chem-Bio](https://feeny.ai/job/senior-software-engineer-chem-bio-ai-security-institute-london-2k1b3mjkxd25) — London, United Kingdom