What You’ll Work On
- Reasoning via reinforcement learning: Designing and training reasoning systems using RLHF, RLAIF, and reward modeling approaches, applied to geological hypothesis generation and evaluation.
- Process reward models and verifiers: Developing fine‑grained supervision over intermediate reasoning steps - not just final answers - so the system learns to reason well, not just get lucky.
- Search and planning: Exploring chain-of-thought strategies, search-time compute (e.g., Monte Carlo Tree Search), and other techniques that enable deeper, more deliberate reasoning over geological evidence.
- Scalable oversight: Contributing to alignment and oversight research - figuring out how to reliably supervise models on geological tasks where ground truth is expensive, delayed, or ambiguous.
- Infrastructure and experimentation: Building robust training pipelines, running large-scale experiments, and iterating quickly across the research-to-production lifecycle.
- Evaluation: Contributing to meaningful benchmarks and evaluation methods for geological reasoning capabilities.
What We’re Looking For
- Strong fundamentals in machine learning, with hands-on experience training large models (LLMs preferred but not required).
- Demonstrated experience with reinforcement learning - ideally applied to language models, but strong RL backgrounds from other domains (robotics, game-playing, scientific discovery) are valued.
- Comfort working across the research-engineering spectrum: you can write a paper and you can debug a distributed training job.
- Familiarity with at least some of: reward modeling, RLHF/RLAIF pipelines, search and planning methods, or AI alignment techniques.
- Publication record is a plus but not a strict requirement - we care more about the quality of your thinking and what you’ve built.
For Interns
We welcome outstanding PhD and Masters students (and exceptional undergraduates) for research internships typically lasting 12-16 weeks. Interns work on the same problems as full-time researchers, embedded in a team and owning a meaningful project from day one. What we look for in intern candidates:
- Currently pursuing a graduate degree (PhD or Masters) in machine learning, AI, or a related field - or an undergraduate with significant research experience.
- Coursework or research experience in reinforcement learning, NLP, or deep learning.
- A strong project portfolio or publications demonstrating independent research ability.
- Eagerness to tackle open-ended problems and ship real experiments on real data.
At More Senior Levels, We’d Also Expect
- A track record of identifying and driving high-impact research directions independently.
- Experience mentoring other researchers and influencing technical strategy.
- Deep expertise in one or more of the core technical areas listed above.