United Kingdom
United StatesResearch Scientist (Control)
8 мес. назад
United KingdomUnited StatesWorldwideOnsite
researchdata analysisalgorithm design
Research Scientist role focused on AI control research to develop practical tools reducing AI risks.
О компании
- Application deadline: We are conducting interviews actively and aim to fill this role as soon as we find someone suitable. THE OPPORTUNITY Join our new AGI safety product team and help transform AI control research into practical tools that directly reduce risks from AI. As an Research Scientist (Control), you’ll work closely with Marius (CEO & currently leads the monitoring efforts), other control researchers and product engineers. We are currently building Watcher , a monitoring tool for coding agents. Our monitoring research agenda attempts to translate compute into safety at scale. You will join a small team and will have significant ability to shape the team & tech, and have the ability to earn responsibility quickly. You will
Требования
- 2+ years of experience conducting empirical research with large language models or AI systems
- Strong experience with AI coding agents. For example, having extensively used and compared frontier coding agents, or having designed / developed coding agents
- Experience with LLM-as-a-judge setups or AI monitoring more broadly
- Experience designing and running experiments, analyzing results, and iterating based on empirical findings e.g. prompting, scaffolding, agent design, fine-tuning, or RL
- Strong Python programming skills
- Demonstrated ability to work independently on open-ended research problems
- Familiarity with AI safety concepts, particularly agent-related risks
- Familiarity with computer security, e.g. security testing and secure system design
- Experience fine-tuning language models or working with smaller open-source models
- Previous work building developer tools or monitoring systems
- Publications or contributions to AI safety or ML research
- Experience with production log systems or production log analysis
Условия
- This role offers market competitive salary, equity, and competitive benefits.
- Salary: 100k - 200 GBP (~150k - 270k USD)
- Flexible work hours and schedule
- Unlimited vacation
- Unlimited sick leave
- Up to 6 months of paid parental leave
- Comprehensive health, dental and vision insurance
- Retirement savings with competitive employer matching (e.g. 401(k) for US employees)
- Lunch, dinner, and snacks are provided for all employees on workdays
- Paid work trips, including staff retreats, business trips, and relevant conferences
- A yearly $1,000 (USD) professional development budget
- Relocation support and visa fees (if applicable)
Другое
- Build a comprehensive failure mode database : Systematically collect and categorize 100+ distinct AI agent failure modes across safety and security dimensions, creating the foundation for our monitoring library.
- Develop and validate monitoring approaches : Create and empirically test monitoring prompts and strategies for key failure categories, establishing clear metrics for monitor performance and building evaluation frameworks to track progress.
- Optimize the monitoring pipeline : Improve log preprocessing and monitor scaffolding to achieve measurable improvements in detection accuracy, false positive rates, and computational efficiency.
- Advance monitoring capabilities : Work on advanced approaches such as fine-tuned monitors or agentic investigation systems
- Hierarchical monitoring for coding agent security : Design a multi-layer monitoring system for detecting security vulnerabilities introduced by coding agents. Start by cataloging common security failure modes (e.g., hardcoded credentials, SQL injection vulnerabilities, insecure API calls). Build specialized monitors for each category, then create a hierarchical system where fast, efficient first-pass monitors flag potentially problematic code for deeper investigation by more sophisticated monitors.
- Design a backtesting strategy for Watcher: Validate the system on synthetic test cases and real agent outputs, iterating to optimize the tradeoff between detection rates and false positives while maintaining low latency for most monitoring decisions.
- Fine-tune an open-source model to be a great monitor: Take an open-source model and fine-tune it on our large dataset of coding agent failures with high-quality ground truth labels. Test different fine-tuning techniques and measure generalization to our held-out data. Compare against prompted baselines on accuracy, cost and latency. The goal is to fine-tune models to lift the pareto frontier of monitors.
- Time Allocation : Full-time
- Location : This is an in-person role working out of our London or San Francisco office. We offer flexible working hours and wfh arrangements.
- Visa sponsorship: We sponsor visas in both the UK and US. Sponsorship isn't guaranteed for every role or candidate, but if we make you an offer, we'll work with you to find the right visa route.