Research Engineer: Human Influence & AI Safety

AI Security Institute; Greater London; Hybrid; GBP 65,000 - 145,000; Full time

Benefits offered by this job

Pre-release model access

Ample compute

Publication opportunities

Learning stipend

Conference funding

Job summary

AI Security Institute, based in London, seeks a Research Engineer to advance our Human Influence program through scalable RL post-training, evaluation pipelines, and rigorous experimentation on frontier AI safety. You will work alongside researchers and engineers, deploying robust ML systems and contributing to policy-relevant AI governance discussions.

Join a hyper-impactful team with access to pre-release models, ample compute, and opportunities to publish.

Qualifications

• Proven experience deploying a benchmark, evaluation, or product to users.
• Clear understanding of the current AI safety literature, and interest in Human Influence topics.
• Clear and consistent communication.
• Clear understanding of fundamental Machine Learning concepts.

Responsibilities

• Designing and building a Reinforcement Learning environment aimed at mitigating model deception in one-to-one conversations or multi-agent threads.
• Leveraging interpretability methods to identify why models exhibit concerning behavior and designing mitigations.
• Building the scalable system architecture underpinning repeatable delivery and analysis of model evaluations and benchmarks.
• Delivering ambitious, engineering-heavy research projects on Human Influence topics using post-training techniques on large compute clusters.

Skills

Reinforcement Learning

Python

PyTorch

JAX

Keras

Docker

Kubernetes

Tools

Docker

Kubernetes

Ray

FastAPI

SLURM

Job description

AI Security Institute, based in London, seeks a Research Engineer to advance our Human Influence program through scalable RL post-training, evaluation pipelines, and rigorous experimentation on frontier AI safety. You will work alongside researchers and engineers, deploying robust ML systems and contributing to policy-relevant AI governance discussions.

Join a hyper-impactful team with access to pre-release models, ample compute, and opportunities to publish.