Job Description
You will like this opportunity if you're passionate about using empirical research to make AI systems safer in practice. You enjoy the challenge of translating theoretical AI risks into concrete detection mechanisms. You thrive on rapid iteration and learning from data. You want your research to directly impact real-world AI safety.
Research & Development
- Systematically collect and catalog coding agent failure modes from real-world instances, our internal deployments, public examples, research literature, and theoretical predictions
- Design and conduct experiments to test monitor effectiveness across different failure modes and agent behaviors
- Build and maintain evaluation frameworks to measure progress on monitoring capabilities
- Build and maintain high-quality datasets to train and test monitors on
- Iterate on monitoring approaches based on empirical results, balancing detection accuracy with computational efficiency
- Stay current with research on AI safety, agent failures, and detection methodologies
- Stay current with research into coding security and safety vulnerabilities
Monitor Design & Optimization
- Develop & maintain a comprehensive library of monitoring prompts tailored to specific failure modes (e.g., security vulnerabilities, goal misalignment, deceptive behaviors)
- Experiment with different reasoning strategies and output formats to improve monitor reliability
- Design and test hierarchical monitoring architectures and ensemble approaches
- Optimize log pre-processing pipelines to extract relevant signals while minimizing latency and computational costs
- Implement and evaluate different scaffolding approaches for monitors, including chain-of-thought reasoning, structured outputs, and multi-step verification
Fine-tuning & Red-teaming
- Fine-tune open-source models to create efficient monitors for high-volume production environments
- Design and build agentic monitoring systems that autonomously investigate logs to identify both known and novel failure modes
- Build automated red-teaming pipelines that attack monitors at scale
- Design iterative adversarial games where a red-team and blue team continuously attack and defend respectively
You will like this opportunity if you're passionate about using empirical research to make AI systems safer in practice. You enjoy the challenge of translating theoretical AI risks into concrete detection mechanisms. You thrive on rapid iteration and learning from data. You want your research to directly impact real-world AI safety.
Research & Development
- Systematically collect and catalog coding agent failure modes from real-world instances, our internal deployments, public examples, research literature, and theoretical predictions
- Design and conduct experiments to test monitor effectiveness across different failure modes and agent behaviors
- Build and maintain evaluation frameworks to measure progress on monitoring capabilities
- Build and maintain high-quality datasets to train and test monitors on
- Iterate on monitoring approaches based on empirical results, balancing detection accuracy with computational efficiency
- Stay current with research on AI safety, agent failures, and detection methodologies
- Stay current with research into coding security and safety vulnerabilities
Monitor Design & Optimization
- Develop & maintain a comprehensive library of monitoring prompts tailored to specific failure modes (e.g., security vulnerabilities, goal misalignment, deceptive behaviors)
- Experiment with different reasoning strategies and output formats to improve monitor reliability
- Design and test hierarchical monitoring architectures and ensemble approaches
- Optimize log pre-processing pipelines to extract relevant signals while minimizing latency and computational costs
- Implement and evaluate different scaffolding approaches for monitors, including chain-of-thought reasoning, structured outputs, and multi-step verification
Fine-tuning & Red-teaming
- Fine-tune open-source models to create efficient monitors for high-volume production environments
- Design and build agentic monitoring systems that autonomously investigate logs to identify both known and novel failure modes
- Build automated red-teaming pipelines that attack monitors at scale
- Design iterative adversarial games where a red-team and blue team continuously attack and defend respectively
The rapid rise in AI capabilities offer tremendous opportunities, but also present significant risks. At Apollo Research, we’re primarily concerned with risks from Loss of Control, i.e. risks coming from the model itself rather than e.g. humans misusing the AI. We’re particularly concerned with deceptive alignment / scheming, a phenomenon where a model appears to be aligned but is, in fact, misaligned and capable of evading human oversight. We work on the detection of scheming (e.g., building evaluations), the science of scheming (e.g., model organisms), and scheming mitigations (e.g., anti-scheming and control). We closely work with multiple frontier AI companies, e.g. to test their models before deployment or collaborate on scheming mitigations. At Apollo, we aim for a culture that emphasizes truth-seeking, being goal-oriented, giving and receiving constructive feedback, and being friendly and helpful. If you’re interested in more details about what it’s like working at Apollo, you can find more information here.
We're now also developing tools and products (See Watcher) that make it easier to prevent harms from AI systems widely deployed AI systems.
Equality Statement: Apollo Research is an Equal Opportunity Employer. We value diversity and are committed to providing equal opportunities to all, regardless of age, disability, gender reassignment, marriage and civil partnership, pregnancy and maternity, race, religion or belief, sex, or sexual orientation.