FREE ACCESS
5,000–10,000 jobs/day
See all jobs on Scoutfield
Search thousands of fresh jobs every day.
Discover
- Fresh listings
- Fast filters
- No subscription required
Create a free account and start exploring right away.
Core Competencies
Role fitCore Competencies
Use this summary to align your resume positioning with the role.
Demonstrates expertise in AI safety research, with a strong foundation in machine learning and transformer architectures. Proficient in developing Python research code and applying interpretability techniques to ensure safe AI deployment.
Highest-signal resume keywords
Machine Learning FundamentalsTransformer ArchitecturesPython ProgrammingPyTorch FrameworkWhite-Box and Black-Box Interpretability
ATS Keywords
Tailor your resumeApplicant Tracking System Keywords
Tip: use these terms in your resume and cover letter to boost ATS matches.
Hard Skills
Machine LearningTransformer ArchitecturesPython ProgrammingDeep Learning FrameworksResearch Code DevelopmentVersion Control with GitExperimental DesignTechnical DocumentationHypothesis FormulationAI Safety Areas
Soft Skills
Excellent CommunicationCuriosityAnalytical Rigor
Tools & Technologies
PyTorchGit
Industry Keywords
AI SafetyRobustnessEvaluationsUncertainty CalibrationTechnical Research
Tech Stack
Tools & technologiesPythonPyTorch
About the role
Key responsibilities & impact- Conduct original technical research in AI safety to support safe, trustworthy AI deployment
- Design and run experiments to study and steer model behaviour
- Apply white-box and black-box methodologies to transformer-based LLMs
- Develop modular, reproducible Python research code using frameworks such as PyTorch
- Build and maintain research infrastructure and technical tooling
- Document and communicate findings through academic papers, technical reports, and presentations
- Collaborate with senior scientists to identify literature gaps, refine hypotheses, and define research scope
- Translate technical insights for frontier labs, government bodies, external partners, and safety institutes
Requirements
What you’ll need- Solid background in machine learning fundamentals and transformer architectures, specifically LLMs
- Practical understanding of white-box and black-box interpretability techniques, such as steering vectors or mechanistic interpretability
- Demonstrated capability to formulate hypotheses from structured technical problems
- Strong programming skills in Python and deep learning frameworks such as PyTorch
- Track record of writing clean, modular research code
- Experience using Git for version control
- Excellent communication skills for translating complex technical concepts and experimental results into clear reports and presentations
- Curiosity and analytical rigour
- Exposure to AI safety areas such as robustness, evaluations, or uncertainty calibration
- Must answer whether visa sponsorship is required to work in the UK
Benefits
Comp & perks- The company is open to conversations about part-time hours
- Human review of every application, never decided by AI
- Candidates may use AI for research and interview preparation
- AI note-taker use in interviews can be opted out of