You and the process

With a person
Anna, in-house recruiter
9 years hiring engineers
30 minutes with a real recruiter
They read your CV with you, on a call, and say where the offers are being lost.
Didn’t find what you were looking for? Tell us what to build
Early Window: Closes in
Company hidden

Software Engineer

  • Hybrid
  • 3-6 years

Salary

£65,000/ year

AI summary

For members

The whole posting in a few lines. Sign up to read it here and on every role you open.

Sign Up to Read

Description

The company is a UK government team that studies advanced AI risks and turns that work into action. It sits close to the Prime Minister's office and works with frontier AI developers and governments around the world.

The Red Team finds and stress tests weaknesses in frontier AI systems and shares its findings with leading AI companies, UK officials and allied governments. Demand for this work is rising faster than the team can meet it, so the team is growing.

The Red Team has three sub-teams. Misuse stress tests and jailbreaks safeguards against misuse of dangerous capabilities. Alignment detects and studies misalignment and loss-of-control risks. Control stress tests measures that stop AI agents from taking harmful actions. Each sub-team has its own focus but shares methods, infrastructure and tooling.

The team is hiring software engineers at every level, from junior to principal. The role may not suit you if you want production-grade software over rapid prototyping, or if you prefer fixed requirements and long planning cycles, since priorities shift with each new model and deadlines are tight.

The deadline to apply is end of day on Tuesday 8th December, anywhere on Earth.

The selection process may vary, but expect a technical proficiency test, conversations with a cross-section of AISI staff including non-technical colleagues, and a conversation with your team lead. Stages can include an initial assessment, a screening call, a technical assessment, a behavioural interview and a final interview with senior leadership.

Responsibilities

  • Build and maintain systems that run red teaming against frontier models at scale, such as automated jailbreaking pipelines, alignment auditor agents in Inspect Petri and attacker agents for control red teaming.
  • Design and build systems that run large-scale automated research and engineering with many agents on AISI's research platform.
  • Extend Inspect-based evaluation tooling, which AISI open-sourced for evaluating AI, so it works with new kinds of targets.
  • Solve performance, reliability and security problems that come up when thousands of agents run in parallel.
  • Share infrastructure with the Core Technology team to avoid duplicated work.
  • Help run pre-release testing of frontier models, often against tight deadlines.
  • Debug issues as they arise and make sure results are reliable and reproducible.
  • Turn loosely defined research ideas into tested, documented and maintainable code.
  • Review code, share knowledge and help researchers write better software.

Requirements

  • Write production-quality code at pace.
  • Design, ship and maintain complex technical products.
  • Raise technical standards across a team through mentoring and feedback.
  • Communicate clearly in writing and speech.
  • Work effectively with many people, including external teams.
  • Have experience working in a world-class research team made up of scientists and engineers, such as one at a top-3 lab.
  • Be interested in automating work with agents while accounting for their limitations.
  • Use Python.
  • Have built and maintained systems on AWS or another cloud provider using infrastructure as code.
  • We are especially keen on people who have worked closely with research teams, understood their needs, built tools they want to use and automated their workflows.
  • We are especially keen on people with a solid grasp of frontier AI capabilities, limits and risks, and how they can be used to automate work at scale.
  • We are especially keen on people who have built infrastructure that runs at scale with a high bar for security.
  • We are especially keen on people who have served and trained models.
  • Highly desirable: cloud infrastructure or DevOps expertise with AWS, Azure, Kubernetes, Terraform, CDK, Docker or similar.
  • Highly desirable: cybersecurity expertise.
  • Highly desirable: ML Ops experience with tools such as vLLM, agent frameworks, fine-tuning or RAG systems.
  • Highly desirable: experience with red teaming, adversarial machine learning or offensive security, such as penetration testing or capture-the-flag competitions.
  • Highly desirable: hands-on work with large language model APIs and their tooling, such as OpenAI-compatible APIs, agent frameworks or vLLM.
  • Highly desirable: experience building, running or analysing AI evaluations, ideally with Inspect.
  • Highly desirable: cloud and DevOps work with AWS, Kubernetes, Docker, Terraform or similar.
  • Highly desirable: familiarity with how AI could be misused or escape human control, and how safeguards try to stop this.

Conditions

Salaries are set by role scope and relevant experience. Most offers fall between £65,000 and £145,000, paid as a base salary plus a technical allowance, where take-home pay equals base plus technical allowance.

This role sits outside the DDaT pay framework because it needs deep technical expertise in frontier AI safety, robustness and advanced AI architectures.

Level 3 pays £65,000 to £75,000, made up of a base of £40,850 and a technical allowance of £24,150 to £34,150.

Level 4 pays £85,000 to £95,000, made up of a base of £48,540 and a technical allowance of £36,460 to £46,460.

Level 5 pays £105,000 to £115,000, made up of a base of £63,165 and a technical allowance of £41,835 to £51,835.

Level 6 pays £125,000 to £135,000, made up of a base of £76,475 and a technical allowance of £48,525 to £58,525.

Level 7 pays £145,000, made up of a base of £76,475 and a technical allowance of £68,525.

Successful candidates must pass a criminal record check and obtain baseline personnel security standard (BPSS) clearance before appointment. Eligibility for counter-terrorist check (CTC) clearance is strongly preferred, and any higher clearance needed for a role will be stated in the advertisement.

Candidates dismissed, or who would have been dismissed, for internal fraud in participating government bodies are banned from civil service employment for 5 years, and pre-employment checks look for known fraudsters reapplying.

The company may be able to offer roles to applicants of any nationality or background, so please apply even if you do not meet the standard nationality requirements.

The Civil Service embraces diversity and equal opportunity, runs the Disability Confident Scheme for disabled candidates who meet the minimum criteria, and offers a Redeployment Interview Scheme to civil servants at risk of redundancy who meet the minimum requirements.

Benefits

  • Work with people who are very talented, driven and supportive.
  • Influence how frontier AI is governed and deployed worldwide.
  • Work with the Prime Minister's AI Advisor and leading AI companies.
  • Help build the first and best-resourced public-interest research team focused on AI security.
  • Get pre-release access to several frontier models and plenty of compute.
  • Receive substantial operational support so you can focus on research and ship quickly.
  • Work alongside experts in national security, policy, AI research and related sciences.
  • Take ownership of important problems early if you are talented and driven.
  • Pursue research ideas without product pressure.
  • Publish and collaborate externally.
  • Work from a modern central London office, or where applicable from similar government offices in Birmingham, Cardiff, Darlington, Edinburgh, Salford or Bristol, with hybrid working and occasional remote work abroad.
  • Receive stipends for home working equipment.
  • Enjoy at least 25 days of annual leave, 8 public holidays, extra team-wide breaks and 3 days off for volunteering.
  • Get generous paid parental leave: 36 weeks of UK statutory leave shared between parents, 3 extra paid weeks, and the option of more unpaid time.
  • Choose between the Partnership pension, which needs no employee contributions and carries up to 14.75% employer contributions, or the Alpha defined benefit pension, which pays a guaranteed, inflation-linked income for life.
  • Get discounts and benefits for cycling to work, donations, retail and gyms.
  • These benefits apply to direct employees. Benefits may differ for people joining through other arrangements such as secondments.

Where you’d work

Part of the week in the office

You can work from

  • United Kingdom

About the company

Company hidden

Office in London, United Kingdom

Your chances

Still hiring, not crowded yet, and you'd be among the first.

  • 17 checks run
  • 5 good signs
  • 0 red flags

Still hiring?

11 checks

Actively hiring

In its favour3

  • Still on the company's own careers site, checked 1 h agoModerate evidence
  • Found in the last 48 hours, before the big job boardsModerate evidence
  • States its salary: £65KSlight evidence

How crowded?

6 checks

Low

In its favour2

  • In its Early Window: not on the big job boards yetStrong evidence
  • Hybrid in London: only people nearby can take itSlight evidence

Fits Me

How well does this role fit you?

Answer a few questions or drop your CV, and every role gets a fit score with the reasons, this one first.

  • Your field
  • Level
  • Stack
  • Work model
  • Salary floor
  • Must-haves
Details10 facts · Role, Location, Compensation
Tech stack
  • Python
  • AWS
  • Kubernetes
  • Docker
  • Terraform
  • Azure
  • LLMs
  • RAG
Specialty
Security
Region
United Kingdom
Pay period
Annual
Show 6 more factsShow less

Role

Category
DevOps & Infrastructure
Specialty
Security
Experience
5+ years
Tech stack
  • Python
  • AWS
  • Kubernetes
  • Docker
  • Terraform
  • Azure
  • LLMs
  • RAG

Location

Work model
Hybrid
Region
United Kingdom
Office
  • London, United Kingdom
Remote from
  • United Kingdom

Compensation

Salary
£65,000 / year
Pay period
Annual

Something wrong with this vacancy?

Similar vacancies

Share this vacancy

What's wrong with it?

The employer never sees who reported.

Reason