Effective Altruism Global
Research Manager
How your CV stacks up
Upload your CV to see how well it fits this job role
?%
LASR Labs
Expression of Interest Form
Applications for our Summer 2026 cohort (20th July — 16th October) are now closed. Feel free to fill out our expression of interest form to be notified when the next application round opens.
About LASR
London AI Safety Research Labs is a technical AI Safety research programme focussed on reducing the risk of loss of control to advanced AI. We focus on action-relevant questions tackling concrete threat models. Participants work in teams of three to four, supervised by an experienced AI safety researcher, to write an academic-style paper and accompanying blog post. Teams work full-time and in person from the London Initiative for Safe AI. The programme is designed to “learn by doing”; taking a research project from proposal all the way to publication.
We expect LASR Labs to be a good fit for applicants looking to join technical AI safety teams in the next year. Alumni from previous cohorts have gone on to work at UK AISI, Apollo Research, Leap Labs, and Open Philanthropy. Many more have continued working with their supervisors or are doing AI Safety research in their PhD programmes. LASR will also be a good fit for someone hoping to publish in academia; four out of five groups in 2023 had papers accepted to workshops (at NeurIPS) or conferences (ICLR). All five papers from the Summer 2024 cohort were accepted to workshops at NeurIPs.
Programme Details
LASR Labs is a 13 week programme which runs twice a year. Participants receive an £11,000 stipend to cover living expenses in London, and we will also provide food, office space, and travel.
In week 0, you will learn about and critically evaluate a handful of technical AI safety research projects with support from LASR. Developing an understanding of which projects might be promising is difficult and often takes many years, but is essential for producing useful AI safety work. Week 0 aims to give participants space to develop their research prioritisation skills and learn about various different agendas and their respective routes to value. At the end of the week, participants will express preferences about their preferred projects, and we will match them into teams.
In the remaining 12 weeks, you will write and then submit an AI safety research paper (as a preprint, workshop paper, or conference paper).
Reasons to use Rodeo
Start with a chat, not a search bar
Grad scheme, placement, apprenticeship? Not sure what you want yet — that's fine. Your agent talks it through with you and turns "I have no idea" into a shortlist.
It searches the market for you
Every day your agent scans the market matching roles against what actually matters to you, not just keywords on a CV.
Only hits
No noise. No "maybe this fits." Just roles with a clear explanation of why they're right — and where to focus when applying.
Topics and supervisors
Previous LASR groups have published on important areas in AI safety, focused on reducing risks from advanced AI. We’ve had supervisors from Google DeepMind, UKAISI, and top UK universities.
In earlier rounds, participants have worked on projects relating to: untrusted monitoring in AI control, data poisoning, interpretability probes, steganography, sparse auto encoders, and evaluating scheming. We’re also excited about a range of other areas, including automated alignment, developmental interpretability, and studying personas.
Who should apply?
We Are Looking For Applicants With The Following Skills
- Technical ability: Machine learning engineering experience and strong quantitative skills.
- Research ability: Willingness to experiment, iterate, and dive into execution under uncertainty. An ability to develop a theory of change for a project focussed on impact.
- Communication skills: An ability to clearly articulate the outcomes and implications of experiments, coupled with transparent reasoning.
For more detail on how we think about and measure technical and research ability, refer to “tips for empirical alignment research” by Ethan Perez, which outlines in detail the specific skills valued within an AI safety research environment.
There are no specific requirements for experience, but we anticipate successful applicants will have done some of these things:
- Conducted research in a domain relevant to the topics below or research at the intersection of your domain and frontier AI systems.
- Experienced working with LLMs.
- Completed or in the process of a PhD in a relevant field like Computer Science, Physics, Maths, etc.
Research shows that people from underrepresented groups are more prone to experiencing imposter syndrome and doubting the strength of their candidacy, so we urge you not to exclude yourself prematurely and to submit an application if you're interested in this work.
Past Projects
- A is for Absorption: Studying Feature Splitting and Absorption in Sparse Autoencoders
- David Chanin*, James Wilken-Smith*, Tomáš Dulka*, Hardik Bhatnagar*, Joseph Bloom
- View Paper
Get help with your application
Your very own career expert that helps elevate your application to the next level.
-
Hidden in Plain Text: Emergence and Mitigation of Steganographic Collusion in LLMs
- Yohan Mathew*, Ollie Matthews*, Robert McCarthy*, Joan Velja*, Dylan Cope, Nandi Schoots
- View Paper
-
Reinforcement Learning Fine-tuning of Language Models is Biased Towards More Extractable Features
- Diogo Cruz, Edoardo Pona, Alex Holness-Tofts, Elias Schmied, Víctor Abia Alonso, Charlie Griffin, Bogdan-Ionut Cirstea
- View paper
-
Honesty to Subterfuge: In-Context Reinforcement Learning Can Make Honest Models Reward Hack
- Leo McKee-Reid*, Maria Angelica Martinez*, Joe Needham*, Christoph Sträter*, Mikita Balesni
- View Paper
-
Characterizing stable regions in the residual stream of LLMs
- Jett Janiak, Jacek Karwowski*, Chatrik Singh Mangat*, Nora Petrova, Giorgi Giglemiani, Stefan Heimersheim
- View Paper
-
Tall Tales at Different Scales: Evaluating Scaling Trends For Deception in Language Models
- Francis Rhys Ward, Felix Hofstätter, Louis Alexander Thomson, Harriet Mary Wood, Oliver Jaffe, Patrik Bartak, Samuel F. Brown
- View paper
-
Defining and Mitigating Collusion in Multi-Agent Systems
- Jack Foxabbott, Sam Deverett, Kaspar Senft, Samuel Dower, Lewis Hammond
- View paper
-
Comparing Optimization Targets for Contrast-Consistent Search
- Hugo Fry, Seamus Fallows, Ian Fan, Jamie Wright, Nandi Schoots
- View paper
-
On The Expressivity of Objective-Specification Formalisms in Reinforcement Learning
- Rohan Subramani, Marcus Williams, Max Heitmann, Halfdan Holm, Charlie Griffin, Joar Skalse
- View paper
-
Evaluating Synthetic Activations composed of SAE Latents in GPT-2
- Giorgi Giglemiani*, Nora Petrova*, Chatrik Singh Mangat*, Jett Janiak, Stefan Heimersheim
- View Paper
“It took my CV and asked me questions relevant to understanding what kind of jobs to suggest for me. Suggestions were almost perfect. Jobs were exactly what I’ve been looking for.”
Jessica, London
Skills
Location