Research Scientist / Research Engineer (AI Safety Institute)
Department for Science, Innovation & Technology
Apply before 11:55 pm on Wednesday 11th September 2024
Details
Reference number
Salary
Job grade
Contract type
Secondment
Length of employment
Business area
Type of role
Working pattern
Number of jobs available
Contents
Location
About the job
Job summary
About the AI Safety Institute
The AI Safety Institute is the first state-backed organisation focused on advancing AI safety for the public interest. We launched at the Bletchley Park AI Safety Summit in 2023 because we believe taking responsible action on this extraordinary technology requires a capable and empowered group of technical experts within government.
We have ambitious goals and need to move fast.
- Develop and conduct evaluations on advanced AI systems. We will characterise safety-relevant capabilities, understand the safety and security of systems, and assess their societal impacts.
- Develop novel tools for AI governance. We will create practical frameworks and novel methods to evaluate the safety and societal impacts of advanced AI systems, and anticipate how future technical safety research will feed into AI governance.
- Facilitate information exchange. We will establish clear information-sharing channels between the Institute and other national and international actors. These include stakeholders such as policymakers and international partners.
Our staff includes senior alumni from OpenAI, Google DeepMind, start-ups and the UK government, and ML professors from leading universities. We are now calling on the world’s top technical talent to join us. This is a truly unique opportunity to help shape AI safety at an international level.
As more powerful models are expected to hit the market over the course of 2024, AISI’s mission to push for safe and responsible development and deployment of AI is more important than ever.
What we value:
- Diverse Perspectives: We believe that a range of experiences and backgrounds is essential to our success. We welcome individuals from underrepresented groups to join us in this crucial mission.
- Collaborative Spirit: We thrive on teamwork and open collaboration, valuing every contribution, big or small.
- Innovation and Impact: We are dedicated to making a real-world difference in the field of frontier AI safety and capability, and we encourage innovative thinking and bold ideas.
- Our Inclusive Environment: We are building an inclusive culture to make the Department a brilliant place to work where our people feel valued, have a voice and can be their authentic selves. We value difference and diversity, not only because we believe it is the right thing to do, but because it will help us be more innovative and make better decisions.
Job description
As a Research Scientist or Research Engineer at AISI, you will help to set our direction for AI system evaluations, including large language models (LLMs), and build & maintain robust evaluation frameworks for these AI systems. You will lead and contribute to projects designed to be integrated into our evaluation suite, evaluating the capabilities and safeguards of cutting-edge models, as well as more speculative research work aimed at mitigations and system understanding.
We draw on a wide range of disciplines, and value a diversity of research expertise across our five workstreams. You will be primarily associated with one of our workstreams, however, sometimes your work will intersect multiple workstreams. Our workstreams include:
- Chem/bio: studying how LLMs and more specialised AI systems are advancing biological and chemical capabilities relating to harmful outcomes. This includes potential uplift to novice actors and future scenarios like design of biological agents
- Cyber misuse: studying how LLMs and more specialised AI systems may aid in cyber-criminality and the adequacy of cybersecurity measures against AI systems
- Safeguards: evaluating the strength and efficacy of safety and security components of advanced AI systems against diverse threats which could circumvent safeguards
- Societal impacts: evaluating a range of impacts of advanced models that could have widespread implications for our societal fabric (e.g. undermining trust in information, psychological wellbeing, cognitive wellbeing, unequal outcomes)
- Autonomous systems: Testing for precursors to loss of control by measuring relevant capabilities in long-horizon computer-based tasks. Examples are sub-tasks of autonomous replication, AI development and self-improvement, as well as adaptation to human attempts to intervene and the ability to profitably interact with and manipulate humans. This includes trajectories that start from a misuse event as well as cases of misalignment.
- Platform: The platform team supports AISI with cross-cutting infrastructure and tooling. From interfacing with corporate services to ensure that the Research Unit are able to work on appropriate physical devices, to managing cloud infrastructure, to writing open-source tooling like Inspect, which is used across all workstreams. We also bear a lot of technical responsibility for AISI’s security posture, and work closely with internal and external stakeholders to ensure that the Research Unit can work both effectively and securely.
You will work closely with the Workstream Lead, and other Research Engineers and Research Scientists, as well as benefit from support from our cross-functional Platform Team. You will also collaborate with external topic-level experts, contractors, partner organisations and policy makers to coordinate and build on external research.
There will be significant scope to contribute to the strategy of your workstream team and to design experiments with set-ups of increasing complexity.
This advert is for individuals with strong Research Scientist or Engineering backgrounds, but without existing priors or preference on which of our workstreams to join. If you have an interest in a specific workstream, we encourage you to look at whether these teams are advertising directly. Please do not apply for multiple RS/RE vacancies simultaneously.
Person specification
We look for some of the following skills, experience and attitudes in a Research Scientist or Research Engineer.
- Relevant experience in industry, relevant open-source collectives, or academia in a field related to machine learning, AI, AI security, or computer security
- Experience in building software systems to meet research requirements and have led or been a significant contributor to relevant software projects, demonstrating cross-functional collaboration skills.
- Knowledge of training, fine-tuning, scaffolding, prompting, deploying, and/or evaluating current cutting-edge machine learning systems such as large language models
- Knowledge of statistics
- A strong curiosity in understanding AI systems and studying the security implications of this technology
- Motivated to conduct research that is not only curiosity driven but also solves concrete open questions in governance and policy making
- Ability to work autonomously and in a self-directed way with high agency, thriving in a constantly changing environment and a steadily growing team, while figuring out the best and most efficient ways to solve a particular problem
- Bring your own voice and experience but also an eagerness to support your colleagues together with a willingness to do whatever is necessary for the team’s success and find new ways of getting things done within government
- Have a sense of mission, urgency, and responsibility for success, demonstrating problem-solving abilities and preparedness to acquire any missing knowledge necessary to get the job done
- Comprehensive understanding of large language models (e.g. GPT-4). This includes both a broad understanding of the literature, as well as hands-on experience with things like pre-training or fine tuning LLMs.
The following are also nice-to-have
- Extensive Python experience, including understanding the intricacies of the language, the good vs. bad Pythonic ways of doing things and much of the wider ecosystem/tooling.
- Direct research experience (e.g. PhD in a technical field and/or spotlight papers at NeurIPS/ICML/ICLR).
- Experience working with world-class multi-disciplinary teams, including both scientists and engineers (e.g. in a top-3 lab).
- Experience acting as a bar raiser for interviews
We are interesting hiring individuals at a range of seniority and experience within this team, including for Senior Research Engineer / Research Scientist positions. Calibration on final title, seniority and pay will take place as part of the recruitment process. We encourage all candidates who would be interested in joining to apply.
Core requirements
- You should be able to spend at least 4 days per week working with us
- You should be able to join us for at least 12 months
- You should be able work from our office in London (Whitehall) for parts of the week, but we provide flexibility for remote work
Benefits
The Department for Science, Innovation and Technology offers a competitive mix of benefits including:
- A culture of flexible working, such as job sharing, homeworking and compressed hours.
- Automatic enrolment into the Civil Service Pension Scheme, with an average employer contribution of 27%.
- A minimum of 25 days of paid annual leave, increasing by 1 day per year up to a maximum of 30.
- An extensive range of learning & professional development opportunities, which all staff are actively encouraged to pursue.
- Access to a range of retail, travel and lifestyle employee discounts.
- The Department operates a discretionary hybrid working policy, which provides for a combination of working hours from your place of work and from your home in the UK. The current expectation for staff is to attend the office or non-home based location for 40-60% of the time over the accounting period.
Things you need to know
Selection process details
Application:
To apply for this post, please send us the following documents:
- A CV setting out your career history, with key responsibilities and achievements. Please ensure you provide employment history that relates to the essential and desirable criteria, and that any gaps in employment history within the last 2 years are explained. The CV should not exceed more than 2 x A4 pages and will be attached to your application via the CS Jobs application portal.
- A Statement of Suitability (max 500 words) answering the questions below:
Why are you interested in joining the AISI right now?
What are the most important technical projects UK government needs to undertake within the next few months to advance AI Safety?
What do you want to be doing to drive those projects forward?
Is there anything else about your skills, experience or background you’d like us to be aware of?
Further details around what this will entail are listed on the application form.
The interview process may vary candidate to candidate, however, you should expect a typical process to include some technical proficiency tests, discussions with a cross-section of our team at AISI (including non-technical staff), conversations with your workstream lead. The process will culminate in a conversation with members of the senior team here at AISI.
Sift and interview process
Candidates should expect to go through some or all of the following stages once an application has been submitted:-
- Coding test
- Initial interview
- Technical take home test
- Second interview and review of take home test
- Third stage interview
- Final stage interview
We reserve the right to close this vacancy with a two week notice period if we have received a sufficient number of applications. Please submit your application as early as possible to ensure that you are considered for the role.
Nationality Requirements
If you do not meet the standard nationality requirements as detailed below, then we would still encourage you to submit an application. We may be able to explore other options such as seconding you in from either your current employer or a third party organisation.
Not meeting the nationality rules set out below should not be seen as an automatic barrier to applying for this role.
Further Information
Reasonable Adjustment
We are proud to be a disability confident leader and we welcome applications from disabled candidates and candidates with long-term conditions.
We fully support adjustments throughout our recruitment process and we encourage candidates to discuss their adjustment needs by emailing the job contact which can be found under the contact point for applicants section.
We do not have an exhaustive list of adjustments that we support but just some examples include additional time to complete your application form, behaviour questions up to 72 hours prior to interview and having extra time at interview.
If you are experiencing accessibility problems with any attachments on this advert, please contact the email address in the 'Contact point for applicants' section.
If successful and transferring from another Government Department a criminal record check may be carried out.
Please note terms and conditions are attached. Please take time to read the document to determine how these may affect you.
Any move to the Department for Science, Innovation and Technology from another employer will mean you can no longer access childcare vouchers. This includes moves between government departments. You may however be eligible for other government schemes, including Tax Free Childcare. Determine your eligibility https://www.childcarechoices.gov.uk
DSIT does not normally offer full home working (i.e. working at home); but we do offer a variety of flexible working options (including occasionally working from home).
In order to process applications without delay, we will be sending a Criminal Record Check to Disclosure and Barring Service on your behalf.
However, we recognise in exceptional circumstances some candidates will want to send their completed forms direct. If you will be doing this, please advise Government Recruitment Service of your intention by emailing Pre-EmploymentChecks.grs@cabinetoffice.gov.uk stating the job reference number in the subject heading.
Applicants who are successful at interview will be, as part of pre-employment screening, subject to a check on the Internal Fraud Database (IFD). This check will provide information about employees who have been dismissed for fraud or dishonesty offences. This check also applies to employees who resign or otherwise leave before being dismissed for fraud or dishonesty had their employment continued. Any applicant’s details held on the IFD will be refused employment.
A candidate is not eligible to apply for a role within the Civil Service if the application is made within a 5 year period following a dismissal for carrying out internal fraud against government.
Feedback
Feedback will only be provided if you attend an interview or assessment.
Security
Nationality requirements
Working for the Civil Service
We recruit by merit on the basis of fair and open competition, as outlined in the Civil Service Commission's recruitment principles (opens in a new window).
Diversity and Inclusion
Apply and further information
Contact point for applicants
Job contact :
- Name : active.campaigns@dsit.gov.uk
- Email : active.campaigns@dsit.gov.uk
Recruitment team
- Email : dsitresourcing.grs@cabinetoffice.gov.uk