Talent.com
Google
Research Scientist, Safety Oversight, DeepMindGoogle • London, England, GB
Research Scientist, Safety Oversight, DeepMind

Research Scientist, Safety Oversight, DeepMind

Google • London, England, GB
30+ days ago
Job type
  • Full-time
Job description

hackajob is collaborating with Google to connect them with exceptional professionals for this role.

We aim to turn production data into intelligence on the safety of deployed AI models. Safety Oversight is a new team tasked with using large-scale production traffic and a variety of automated evaluation methods to monitor the safety and alignment of deployed models. Our work will ensure we measure the real-world efficacy of our safety stack—both of in-model safety training and out-of-model safety mitigations to ensure we are effective in our goal of deploying safe models that are used for widespread public benefit.

The Safety Oversight team sits within the GenAI safety organization and is accountable for ensuring that when a model safety issue occurs in production, or when a user is misusing our model at scale, we detect and understand it, so the safety risk can be rapidly mitigated. We will collaborate closely with teams working on safety training and evaluation for Gemini and GenMedia models.

The Generative AI (GenA)I Safety team operates in a fast-paced, highly collaborative environment. We take the possibility of tangibly dangerous model capabilities seriously as AI advances, and we believe that proactive monitoring and deployment-time oversight are critical for safe AI development.

Artificial intelligence will be one of humanity’s most transformative inventions. At Google DeepMind, we are a pioneering AI lab with exceptional interdisciplinary teams focused on advancing AI development to solve complex global challenges and accelerate high-quality product innovation for billions of users. We use our technologies for widespread public benefit and scientific discovery, ensuring safety and ethics are always our highest priority.

We are pushing the boundaries across multiple domains. Our global teams offer diverse learning opportunities and varied career pathways for those driven to achieve exceptional results through collective effort.

Minimum qualifications:

  • PhD in Computer Science, a related field, or equivalent practical experience.
  • Experience in the domain area of generative AI and Large Language Models (LLM).
  • Experience building and shipping technical products.

Preferred qualifications:

  • Master’s degree or PhD in Engineering, Computer Science, or a related technical field.
  • 3 years of experience developing code, running experiments and analyses collaboratively with coding agents.
  • Experience building highly parallelised data pipelines, working on data quality, automated evaluation design and simple statistical modeling.
  • Proven ability in approaching new research questions and implementing technical solutions for them at scale.
  • Ability to use AI every day to build and find ways to push the frontier of model capabilities to accelerate work.

Responsibilities:

  • Build classifiers and data pipelines to detect model misbehavior and misuse end-to-end.
  • Research and develop cross-context monitoring systems to detect coordinated harms, developing novel signal aggregation methods across disparate user sessions to identify large-scale attack vectors.
  • Think critically about novel methods for monitoring using model activations, actions, chains-of-thought and final answers.
  • Collaborate closely with infrastructure teams and data scientists to scale your work and regularly share results with the wider safety team.
Create a job alert for this search

Research Scientist, Safety Oversight, DeepMind • London, England, GB

Similar jobs

Senior AI Safety Research Scientist - Red Team (Hybrid)

Faculty AIGreater London, England, GB
Full-time

Faculty AI is seeking a Senior Research Scientist to join our high-impact R&D team and lead novel research that advances safety in frontier AI.You will drive real-world deployments alongside govern... Show more

 • Promoted

Research Scientist, Robotics, DeepMind

Software CareersGreater London, England, GB
Full-time

Research Scientist, Robotics, DeepMindat DeepMind • London, UKBack to jobs1.Research Scientist, Robotics, DeepMind—D## Research Scientist, Robotics, DeepMindDeepMind20Research ScientistFull-timeLon... Show more

 • Promoted

Optical Research Scientist

CoMindGreater London, England, GB
Full-time

At CoMind, we are developing a non-invasive neuromonitoring technology that will result in a new era of clinical brain monitoring.In joining us, you will be helping to create cutting‑edge technolog... Show more

 • Promoted

Causal Inference Scientist - Incremental Player Value

Sony PlaystationGreater London, England, GB
Full-time

Sony Interactive Entertainment's PlayStation division is seeking a Causal Insights Specialist to transform how we measure and optimise long-term player value.You will build frameworks and apply cau... Show more

 • Promoted

Research Scientist Intern: LLM Foundations & NLP Research

PowerToFlyGreater London, England, GB
Full-time

A leading global information provider is looking for a Research Scientist Intern to innovate in AI research, focusing on large language models and their applications.The intern will work collaborat... Show more

 • Promoted

Senior AI Safety Research Scientist

FacultyGreater London, England, GB
Full-time

A leading AI research company in London is seeking a Senior Research Scientist to lead impactful AI safety research.This role involves driving research themes, engaging stakeholders, and shaping th... Show more

 • Promoted

Research Scientist (Visual Generative AI & World Models)

EngineersOfAIGreater London, England, GB
Full-time

At Graphcore, we’re building the future of AI compute.We’re a team of semiconductor, software and AI experts, with deep experience in creating the complete AI compute stack — from silicon and softw... Show more

 • Promoted

Road Safety Auditor — Vision Zero & Safe System (Hybrid)

WSP in the UK & IrelandGreater London, England, GB
Full-time

WSP in the UK & Ireland is seeking a Road Safety Auditor to join their Liveable Places team in London.This role offers the chance to work on impactful Vision Zero and Road Safety projects across Lo... Show more

 • Promoted

Lead Machine Learning Engineer - Risk Decisioning

CleoGreater London, England, United Kingdom
Full-time

At Cleo, we’re not just building another fintech app.We’re embarking on a mission to fundamentally change humanity’s relationship with money.Imagine a world where everyone, regardless of background... Show more

 • Promoted

ML Research Scientist Intern – Dynamo Guard / Dynamo Eval / AgentWarden

Dynamo AIGreater London, England, GB
Full-time

At Dynamo AI, an ML Research Scientist Intern will focus on advancing the state of AI evaluation, adversarial robustness, and agent security.You will contribute to novel research in model safety, h... Show more

 • Promoted

Senior Research Scientist — World Modeling & Multimodal AI

OdysseyGreater London, England, GB
Full-time

Odyssey is an AI lab pioneering general world models: causal, multimodal systems that learn to predict and interact with the world over long horizons.This foundational technology promises to revolu... Show more

 • Promoted

CDR Vetting Scientist - Carbon Removal Quality & Risk

Seeds RenewablesGreater London, England, GB
Full-time

Seeds Renewables is looking for an individual to lead the delivery of carbon dioxide removal (CDR) projects aimed at scaling carbon removal to gigatonne capacity.Candidates should have an MSc or re... Show more

 • Promoted

Senior Research Scientist | Multimodal Systems

DeepLGreater London, England, GB
Full-time

We are looking for a Senior Research Scientist to lead fine-tuning, post-training, and reinforcement learning for the next generation of DeepL's document translation multimodal and vision models.Th... Show more

 • Promoted

PhD Research Scientist Intern: Groundbreaking LLM Research

Thomson ReutersGreater London, England, GB
Full-time

Thomson Reuters is seeking PhD Research Scientist Interns for research in AI, particularly focused on Machine Learning and NLP.The role requires experience in developing ML approaches and collabora... Show more

 • Promoted

Applied AI Safety Researcher (Product): Build Scalable Monitors

COL LimitedGreater London, England, GB
Full-time

A pioneering AI safety firm in London seeks an Applied Researcher to join their new AGI safety product team.The role involves translating complex AI risks into practical tools, including designing ... Show more

 • Promoted

Applied Scientist I

Entrust CorporationGreater London, England, GB
Full-time

We are looking for an Applied Scientist I to design and train cutting‑edge machine learning solutions related to digital identities.The role focuses on deepfake detection, bias mitigation, document... Show more

 • Promoted

Field Strategy Lead – Shape AI Safety Ventures

AisafetyGreater London, England, GB
Full-time

A nonprofit startup focused on AI safety seeks a Field Strategy Specialist to shape strategies essential for launching new projects that mitigate risks in emerging technologies.The role involves ma... Show more

 • Promoted

Research Scientist - World Models

SpAItial AIGreater London, England, GB
Full-time

SpAItial is pioneering the next generation of World Models, pushing the boundaries of generative AI, computer vision, and the simulation of reality.We are moving beyond 2D pixels to build models th... Show more

 • Promoted

Senior Optical Research Scientist

CoMind Technologies Limited.Greater London, England, GB
Full-time

At CoMind, we are developing a non-invasive neuromonitoring technology that will result in a new era of clinical brain monitoring.In joining us, you will be helping to create cutting-edge technolog... Show more

 • Promoted

Biologics Scientist, ML Platform Lead (Remote, Equity)

BoltzGreater London, England, United Kingdom
Remote
Full-time

Boltz is seeking a Principal Scientist in Biologics to shape Boltz Lab’s platform by translating deep biological insight into ML design and evaluation.You will work with ML researchers to define bi... Show more